A Comprehensive Survey of Continual Learning: Theory, Method and Application
Open accessThe DOI matches its Crossref record; 459 of the 459 references it cites were found in a registry or an index.
Abstract
To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance drop of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative strategies address continual learning, and how they are adapted to particular challenges in various applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Complex skills can be synthesized by composing simpler programs, which compounds VOYAGER's capabilities rapidly over time and alleviates catastrophic forgetting in other continual learning methods [31, 32].”
From Voyager: An Open-Ended Embodied Agent with Large Language Models (2023) · cites this paper as [32]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, these agents are not lifelong learners that can progressively acquire, update, accumulate, and transfer knowledge over extended time spans [31, 32].”
From Voyager: An Open-Ended Embodied Agent with Large Language Models (2023) · cites this paper as [32]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This position also makes memory currently the most practical route to continual learning for deployed agents: retraining the underlying model for every user, task, and correction is rarely feasible, so what the system learns after deployment often depends on what it writes down [26, 67].”
From Agentic Memory Management Is the Next Frontier of Information Retrieval (2026) · cites this paper as [67]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In AI, memory is usually described in terms of persisting state, retaining conversational context, or learning continually without catastrophic forgetting [32, 67].”
From Agentic Memory Management Is the Next Frontier of Information Retrieval (2026) · cites this paper as [67]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The stability–plasticity dilemma is central to CL, as it balances the model’s ability to retain past knowledge (stability) while acquiring new information (plasticity) [61,62].”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [62]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Transformer-Based Architecture [317] has proven effective for both language and vision domains, and become the dominant choice for state-of-the-art foundation models.”
BackgroundExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970 · cited 1×
“According to the learning theory for supervised learning [48], the performance of an old task is improved with replaying more old training samples that approximate its distribution, but resulting in potential privacy issues and a linear increase in resource overhead .”
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“Foundation Model , such as GPT [316] and CLIP [218], demonstrates impressive performance in a variety of down-stream tasks with the use of large-scale pre-training.”
MethodGAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 4×
“erally more efficient than images, IncCLIP [467] replays generated hard negative texts conditioned on images and performs multi-modal knowledge distillation for updating CLIP [347].”
BackgroundMethodInfluentialCommunication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 1×
“of synaptic plasticity” [3], [4], [77], corresponding to the use of meta-learning [118], [185], [360]; and (4) inhibitory synapses for excited neurons to reduce the activity of other neurons [20], [54], [112], [178], which acts similarly to the binary mask for parameter allocation [375], [427].”
MethodOvercoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899 · cited 7×
“The importance can be calculated by the Fisher information matrix (FIM), such as EWC [49] and some more advanced versions [50], [104].”
BackgroundMethodInfluentialAdaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384
McClelland, J. L., McNaughton, B. L., & O'Reilly, R. C. (1995) · Psychological Review · doi:10.1037/0033-295x.102.3.419 · Cited by 5,256 · cited 1×
“A major challenge is known as catastrophic forgetting [6], [7], where adaptation to a new distribution generally results in a largely reduced ability to capture the old ones.”
BackgroundLi, Z., & Hoiem, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2773081 · Cited by 4,202
iCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988 · cited 7×
“iCaRL [356] and EEIL [53] are two early works that perform”
BackgroundMethodInfluentialKnowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931 · cited 1×
“This strategy typically uses the previously-learned model as the teacher and the currently-trained model as the student, while implementing knowledge distillation (KD) [117] to mitigate catastrophic forgetting.”
MethodCatastrophic Interference in Connectionist Networks: The Sequential Learning Problem
McCloskey, M., & Cohen, N. J. (1989) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60536-8 · Cited by 3,770 · cited 1×
“A major challenge is known as catastrophic forgetting [6], [7], where adaptation to a new distribution generally results in a largely reduced ability to capture the old ones.”
BackgroundDiffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
Neural Discrete Representation Learning
Oord, A. V. D., Vinyals, O., & Kavukcuoglu, K. (2017) · arXiv · doi:10.48550/arxiv.1711.00937 · Cited by 2,729 · cited 1×
“To improve storage efficiency, AQM [48] performs online continual compression based on a VQ-VAE framework [414] and saves compressed data for replay.”
MethodFilm: Visual reasoning with a general conditioning layer
Perez, E., Strub, F., De Vries, H., Dumoulin, V., & Courville, A. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11671 · Cited by 2,490
Parameter-efficient transfer learning for NLP
Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., de Laroussilhe, Q., Gesmundo, A., Attariyan, M., & Gelly, S. (2019) · arXiv · doi:10.48550/arxiv.1902.00751 · Cited by 2,270 · cited 3×
“GAN-Memory [80] takes advantage of FiLM [331] and AdaFM [502] to learn task-specific parameters for each layer of a pre-trained generative model, while ADA [111] employs Adapters [165] with knowledge distillation to adjust a pretrained transformer.”
BackgroundMethodThe organization of recent and remote memories
Frankland, P. W., & Bontempi, B. (2005) · Nature Reviews Neuroscience · doi:10.1038/nrn1607 · Cited by 2,138
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953 · cited 1×
“Here, we discuss some attractive intersections of continual learning with other topics of the broad AI community: Diffusion Model [315] is a rising state-of-the-art generative model, which constructs a Markov chain of discrete steps to progressively add random noise for the input and learns to…”
BackgroundContinual Learning Through Synaptic Intelligence
Zenke, F., Poole, B., & Ganguli, S. (2017) · arXiv · doi:10.48550/arxiv.1703.04200 · Cited by 1,784
Metaplasticity: the plasticity of synaptic plasticity
Abraham, W. C., & Bear, M. F. (1996) · Trends in Neurosciences · doi:10.1016/s0166-2236(96)80018-x · Cited by 1,776
A Continual Learning Survey: Defying Forgetting in Classification Tasks
Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3057446 · Cited by 1,647 · cited 2×
“General Continual Learning (GCL) [16], [46], [85] is a broad concept that describes potential challenges in terms of learning paradigms, where the model observes incremental data in an online fashion without explicit task boundaries.”
BackgroundA continual learning survey: Defying forgetting in classification tasks
De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2019) · arXiv · doi:10.48550/arxiv.1909.08383 · Cited by 1,647
Memory Aware Synapses: Learning What (not) to Forget
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., & Tuytelaars, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_9 · Cited by 1,590
Averaging Weights Leads to Wider Optima and Better Generalization
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., & Wilson, A. G. (2018) · arXiv · doi:10.48550/arxiv.1803.05407 · Cited by 1,409
Gradient Episodic Memory for Continual Learning
Lopez-Paz, D., & Ranzato, M. (2017) · arXiv · doi:10.48550/arxiv.1706.08840 · Cited by 1,403 · cited 8×
“Overall performance is typically evaluated by average accuracy (AA) [44], [45] and average incremental accuracy (AIA) [46], [47].”
BackgroundMethodInfluentialContinual Learning with Deep Generative Replay
Shin, H., Lee, J. K., Kim, J., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1705.08690 · Cited by 1,385 · cited 1×
“DGR [160] provides an initial framework in which learning each generation task is accompanied with replaying generated data sampled from the old generative model, so as to inherit the previously-learned knowledge.”
BackgroundLarge Scale Incremental Learning
Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., & Fu, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00046 · Cited by 1,313 · cited 5×
“BiC [147] and WA [148] attribute this issue to the bias of the last fully-connectedlayer,andresolveitbyeitherlearningabiascorrection layerwithabalancedvalidationset[147],ornormalizingthe outputweights[148].”
BackgroundInfluentialSelf-citationRusu, A. A., Rabinowitz, N. C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., & Hadsell, R. (2016) · arXiv · doi:10.48550/arxiv.1606.04671 · Cited by 1,307 · cited 3×
“Except for the TIL setting that always provides the task identity I D t [70], [71], [72], [73], other scenarios generally require the model to determine which θ ( t ) to use based on the input data, as shown in (10).”
A Closer Look at Memorization in Deep Networks
Arpit, D., Jastrzębski, S., Ballas, N., Krueger, D., Bengio, E., Kanwal, M. S., Maharaj, T., Fischer, A., Courville, A., Bengio, Y., et al. (2017) · arXiv · doi:10.48550/arxiv.1706.05394 · Cited by 1,307 · cited 1×
“to capture a distribution, especially for some hard examples [21], [61], [148].”
BackgroundPackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Mallya, A., & Lazebnik, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00810 · Cited by 1,258
Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection
Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., & Yang, J. (2020) · arXiv · doi:10.48550/arxiv.2006.04388 · Cited by 1,241
Learning a Unified Classifier Incrementally via Rebalancing
Hou, S., Pan, X., Loy, C. C., Wang, Z., & Lin, D. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00092 · Cited by 1,195 · cited 7×
“stability, emergent strategies include renormalization of the old and new task solutions [166], [263], [384], [442], balanced exploitation of the old and new training samples [10], [167], [174], [452], [469], [513], reserving space for subsequent tasks [9], [199], [518], etc.”
BackgroundMethodInfluentialEnd-to-End Incremental Learning
Castro, F. M., Marín-Jiménez, M. J., Guil, N., Schmid, C., & Alahari, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01258-8_15 · Cited by 1,184
Stably maintained dendritic spines are associated with lifelong memories
Yang, G., Pan, F., & Gan, W.-B. (2009) · Nature · doi:10.1038/nature08577 · Cited by 1,182 · cited 1×
“Biological neural networks are capable of flexibly modulating synaptic plasticity in response to dynamic inputs, including (1) stabilization of previously-learned synaptic changes to overcome subsequent interference [154], [471], [495], which motivates the strategies of weight regularization to selectively penalize pa…”
BackgroundRiemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Chaudhry, A., Dokania, P. K., Ajanthan, T., & Torr, P. H. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_33 · Cited by 1,091 · cited 6×
“Besides, weight regularization can also be combined with experience replay for better performance and generality [44], [52].”
BackgroundMethodInfluentialHippocampal replay in the awake state: a potential substrate for memory consolidation and retrieval
Carr, M. F., Jadhav, S. P., & Frank, L. M. (2011) · Nature Neuroscience · doi:10.1038/nn.2732 · Cited by 958
Efficient Lifelong Learning with A-GEM
Chaudhry, A., Ranzato, M., Rohrbach, M., & Elhoseiny, M. (2018) · arXiv · doi:10.48550/arxiv.1812.00420 · Cited by 852 · cited 10×
“A-GEM [63] replaces the individual constraints with a global loss of all tasks to improve training efficiency.”
BackgroundMethodInfluentialBourtoule, L., Chandrasekaran, V., Choquette-Choo, C. A., Jia, H., Travers, A., Zhang, B., Lie, D., & Papernot, N. (2021) · 2021 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp40001.2021.00019 · Cited by 810 · cited 1×
“Many efforts in this direction are closely related to continuallearning,suchaslearningseparatemodelswithsubsets oftrainingsamples[307],utilizinghistoricalparametersand gradients[308],removingoldknowledgefromparameterswith Fisherinformationmatrix[309],addingadaptiveparameterson…”
BackgroundHippocampal replay of extended experience
Davidson, T. J., Kloosterman, F., & Wilson, M. A. (2009) · Neuron · doi:10.1016/j.neuron.2009.07.027 · Cited by 806
Learning to Prompt for Continual Learning
Wang, Z., Zhang, Z., Lee, C.-Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., & Pfister, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00024 · Cited by 778 · cited 1×
“Representative strategies include selecting the most relevant prompts from a prompt pool (L2P [205]), optimizing a weighted summation of the prompt pool with attention factors (CODA-Prompt [206]), using explicitly task-sharing and task-specific prompts (DualPrompt [207]) or only task-specific prompts…”
MethodERNIE 2.0: A Continual Pre-Training Framework for Language Understanding
Sun, Y., Wang, S., Li, Y., Feng, S., Tian, H., Wu, H., & Wang, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6428 · Cited by 766
What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated
Kumaran, D., Hassabis, D., & McClelland, J. L. (2016) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2016.05.004 · Cited by 759
Mushroom body output neurons encode valence and guide memory-based action selection in Drosophila
Aso, Y., Sitaraman, D., Ichinose, T., Kaun, K. R., Vogt, K., Belliart-Guérin, G., Plaçais, P.-Y., Robie, A. A., Yamagata, N., Schnaitmann, C., et al. (2014) · eLife · doi:10.7554/elife.04580 · Cited by 696
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.1.1 · Cited by 676
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning
Douillard, A., Cord, M., Ollion, C., Robert, T., & Valle, E. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58565-5_6 · Cited by 638 · cited 8×
“matic representation shifts, PODNet [100] employs a spatial distillation loss to preserve representations throughout the model.”
BackgroundMethodInfluentialExpert Gate: Lifelong Learning with a Network of Experts
Aljundi, R., Chakravarty, P., & Tuytelaars, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.753 · Cited by 619 · cited 2×
“Expert Gate [243] employs a mixture of experts to learn incremental tasks, expanding one expert as each task is introduced.”
BackgroundPiggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights
Mallya, A., Davis, D., & Lazebnik, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_5 · Cited by 613 · cited 1×
“Within a fixed network architecture, Piggyback [221], HAT [71], WSN [222] and H 2 [223] explicitly optimize a binary mask to select dedicated neurons or parameters for each task, with the masked regions of the old tasks (almost) frozen to prevent catastrophic forgetting.”
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Fernando, C., Banarse, D., Blundell, C., Zwólš, Y., Ha, D., Rusu, A. A., Pritzel, A., & Wierstra, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.08734 · Cited by 591 · cited 2×
“PathNet [115] and RPSNet [348] pre-allocate multiple parallel”
BackgroundMethodIncremental Learning of Object Detectors without Catastrophic Forgetting
Shmelkov, K., Schmid, C., & Alahari, K. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.368 · Cited by 559 · cited 3×
“Note that, ak,j can be adapted to other forms depending on the task type, such as average precision (AP) for object detection [384], Intersection-over-Union (IoU) for semantic segmentation [56], Fréchet Inception Distance (FID) for image generation [452], normalized reward for reinforcement learning [10], etc, and the…”
BackgroundMethodTowards Open World Object Detection
Joseph, K. J., Khan, S., Khan, F. S., & Balasubramanian, V. N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00577 · Cited by 544 · cited 1×
“According to the provided X t and Y t in each D t , continual learning is further extended to zero-shot [23], few-shot [24], semi-supervised [25], open-world [26] and un-/self-supervised [27], [28] scenarios.”
MethodDreaming to Distill: Data-Free Knowledge Transfer via DeepInversion
Yin, H., Molchanov, P., Alvarez, J. M., Li, Z., Mallya, A., Hoiem, D., Jha, N. K., & Kautz, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00874 · Cited by 540
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.02643 · Cited by 527
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
Keskar, N. S., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P. T. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.04836 · Cited by 525 · cited 1×
“Therefore, the robustness of an empirical optimal solution θ∗ i to parameter changes is closely related to λ i , which has been commonly used to describe the flatness of loss landscape [162], [211], [309].”
MethodThree scenarios for continual learning
van de Ven, G. M., & Tolias, A. S. (2019) · Lirias · doi:10.48550/arxiv.1904.07734 · Cited by 523 · cited 1×
“Such contents could be new skills, new examples of old skills, different environments, different contexts, etc., with particular realistic challenges incorporated [2], [4].”
BackgroundSharpness-Aware Minimization for Efficiently Improving Generalization
Foret, P., Kleiner, A., Mobahi, H., & Neyshabur, B. (2020) · arXiv · doi:10.48550/arxiv.2010.01412 · Cited by 521 · cited 2×
“SAM [120], [295] encourages finding a wide basin in downstream continual learning by optimizing the flatness metric.”
BackgroundDhar, P., Singh, R. V., Peng, K.-C., Wu, Z., & Chellappa, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00528 · Cited by 516 · cited 2×
“LwM [119] exploits the attention maps of new training samples for KD. EBLL [121] learns task-specific autoencoders and prevents changes in feature reconstruction.”
BackgroundLesort, T., Lomonaco, V., Stoian, A., Maltoni, D., Filliat, D., & Díaz-Rodríguez, N. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.004 · Cited by 506
Few-Shot Class-Incremental Learning
Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., & Gong, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01220 · Cited by 499
Maintaining Discrimination and Fairness in Class Incremental Learning
Zhao, B., Xiao, X., Gan, G., Zhang, B., & Xia, S.-T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01322 · Cited by 494 · cited 4×
“Label Space LwF [252], iCaRL [356], GEM [277], A-GEM [65], EEIL [53], BiC [457], WA [500], DER++ [46], ScaIL [33], S&B [218], SS-IL [11], Coil [506]”
BackgroundInfluentialDeterminantal Point Processes for Machine Learning
Kulesza, A. (2012) · now publishers, Inc. eBooks · doi:10.1561/9781601986290 · Cited by 493
Variational Continual Learning
Nguyen, C. V., Li, Y., Bui, T. D., & Turner, R. E. (2017) · arXiv · doi:10.48550/arxiv.1710.10628 · Cited by 491 · cited 5×
“Here we use VCL [55] as an example, which minimizes the following objective (i.e., maximize its negative): (7) where the KL-divergence can be computed in a closed-form and serves as an implicit regularization term.”
BackgroundMethodInfluentialBrain-inspired replay for continual learning with artificial neural networks
van de Ven, G. M., Siegelmann, H. T., & Tolias, A. S. (2020) · Nature Communications · doi:10.1038/s41467-020-17866-2 · Cited by 474 · cited 4×
“BI-R [412] incorporates context-modulated feedback connections in a standard VAE to replay internal”
BackgroundMethodInfluentialDark Experience for General Continual Learning: a Strong, Simple Baseline
Buzzega, P., Boschini, M., Porrello, A., Abati, D., & Calderara, S. (2020) · arXiv · doi:10.48550/arxiv.2004.07211 · Cited by 473 · cited 6×
“Besides, other realistic consider-ationshavebeenincorporated,suchasmultiplelabels [29],noisy labels [30], blurred boundary [31], [32], hierarchical granularity [33] and sub-populations [34], mixture of task similarity [35], long-tailed distribution [36], novel class discovery [37], [38],…”
BackgroundMethodInfluentialDualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning
Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.-Y., Ren, X., Su, G., Perot, V., Dy, J., et al. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19809-0_36 · Cited by 472
Embracing Change: Continual Learning in Deep Neural Networks
Hadsell, R., Rao, D., Rusu, A. A., & Pascanu, R. (2020) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2020.09.004 · Cited by 467 · cited 5×
“In response to external Manuscript received 13 February 2023; revised 13 September 2023; accepted changes, evolution has empowered human and other organisms with strong adaptability to continually acquire, update, accumulate and exploit knowledge [1], [2], [3].”
BackgroundInfluentialChen, Z., & Liu, B. (2018) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.1007/978-3-031-01581-6 · Cited by 466
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
Prabhu, A., Torr, P. H. S., & Dokania, P. K. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58536-5_31 · Cited by 465 · cited 2×
“GDumb [159] greedily collects incoming training samples in a memory buffer and then uses them to train a model from scratch for testing.”
BackgroundVariational Continual Learning
Turner, R., Bui, T., Li, Y., & Cuong, N. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.35471 · Cited by 438
Coordinated and compartmentalized neuromodulation shapes sensory processing in Drosophila
Cohn, R., Morantte, I., & Ruta, V. (2015) · Cell · doi:10.1016/j.cell.2015.11.019 · Cited by 430
A Survey of Embodied AI: From Simulators to Research Tasks
Duan, J., Yu, S., Tan, H. L., Zhu, H., & Tan, C. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3141105 · Cited by 420
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
Martens, J., & Grosse, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.05671 · Cited by 414 · cited 1×
“To overcome these issues, the Hessian can be approximated by the Fisher information matrix (FIM) ) For ease of computation, the FIM can be further simplified with a diagonal approximation [49], [53] or a Kronecker-factored approximation [50], [54].”
MethodOnline continual learning in image classification: An empirical survey
Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., & Sanner, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.10.021 · Cited by 410
Structural Components of Synaptic Plasticity and Memory Consolidation
Bailey, C. H., Kandel, E. R., & Harris, K. M. (2015) · Cold Spring Harbor Perspectives in Biology · doi:10.1101/cshperspect.a021758 · Cited by 397
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
Golatkar, A., Achille, A., & Soatto, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00932 · Cited by 394
Few-Shot Incremental Learning with Continually Evolved Classifiers
Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., & Xu, Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01227 · Cited by 382 · cited 1×
“[490]), developing a tree-based hierarchical classifier with Gaussian processes (GP-Tree [6]), performing hyperdimen-”
BackgroundOrthogonal Gradient Descent for Continual LearningPreprint
Farajtabar, M., Azizan, N., Mott, A., & Li, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07104 · Cited by 365 · cited 6×
“OGD [113] stores the old gradient directions and rectifies the current gradient orthogonal to them.”
BackgroundInfluentialDyTox: Transformers for Continual Learning with DYnamic TOken eXpansion
Douillard, A., Rame, A., Couairon, G., & Cord, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00907 · Cited by 357 · cited 1×
“lel branches (ACL [107], ReduNet [459], EPIE-Net [104]), adaptive layers (GVCL [276], DyTox [101]), masks or mask”
BackgroundRainbow Memory: Continual Learning with a Memory of Diverse Samples
Bang, J., Kim, H., Yoo, Y., Ha, J.-W., & Choi, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00812 · Cited by 354
Selective Experience Replay for Lifelong Learning
Isele, D., & Cosgun, A. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11595 · Cited by 347
Federated Continual Learning with Weighted Inter-client TransferPreprint
Yoon, J., Jeong, W., Lee, G., Yang, E., & Hwang, S. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03196 · Cited by 343 · cited 1×
“…data collected by clients is dynamic and variable, federated learning needs to overcome catastrophic forgetting and facilitate knowledge transfer across clients, which can be achieved by continual learning strategies such as model decomposition [304] and knowledge distillation [305], [306].”
BackgroundModeling the Background for Incremental Learning in Semantic Segmentation
Cermelli, F., Mancini, M., Rota Bulo, S., Ricci, E., & Caputo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00925 · Cited by 340
Semantic Drift Compensation for Class-Incremental Learning
Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S., & van de Weijer, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00701 · Cited by 340
CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning
Smith, J. S., Karlinsky, L., Gutta, V., Cascante-Bonilla, P., Kim, D., Arbelle, A., Panda, R., Feris, R., & Kira, Z. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01146 · Cited by 334 · cited 2×
“Representative strategies include selecting the most relevant prompts from a prompt pool (L2P [458]), performing a weighted summation of the prompt pool with attention factors (CODAPrompt [402]), using explicitly task-sharing and task-specific prompts (DualPrompt [457]) or only task-specific prompts (S-Prompts [450]),…”
BackgroundMethodClass-incremental Learning via Deep Model Consolidation
Zhang, J., Zhang, J., Ghosh, S., Li, D., Tasci, S., Heck, L., Zhang, H., & Jay Kuo, C.-C. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093365 · Cited by 328 · cited 2×
“Some approaches exploit the unlabeled in-the-wild data to distill the old and new models into a shared model, in order to bridge potential non co-occurrence (BNC [96]) and achieve a better stability-plasticity tradeoff (DMC [493]).”
BackgroundMethodFOSTER: Feature Boosting and Compression for Class-Incremental Learning
Wang, F.-Y., Zhou, D.-W., Ye, H.-J., & Zhan, D.-C. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19806-9_23 · Cited by 327
Encoder Based Lifelong Learning
Rannen, A., Aljundi, R., Blaschko, M. B., & Tuytelaars, T. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.148 · Cited by 324 · cited 2×
“LwM [119] exploits the attention maps of new training samples for KD. EBLL [121] learns task-specific autoencoders and prevents changes in feature reconstruction.”
BackgroundAljundi, R., Kelchtermans, K., & Tuytelaars, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01151 · Cited by 324 · cited 2×
“Potential challenges of the learning paradigm can be summarized in a broad concept called General Continual Learning (GCL) [12], [20], [31], where the model observes incremental data in an online fashion without explicit task boundaries.”
Coresets via Bilevel Optimization for Continual Learning and StreamingPreprint
Borsos, Z., Mutný, M., & Krause, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.03875 · Cited by 310 · cited 1×
“…by maximizing such as the sample diversity of parameter gradients [21], performance of corresponding tasks with cardinality constraints [132], mini-batch gradient similarity and cross-batch gradient diversity [133], ability of optimizing latent decision boundaries [134], diversity of…”
BackgroundContinual learning of context-dependent processing in neural networks
Zeng, G., Chen, Y., Cui, B., & Yu, S. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0080-x · Cited by 309 · cited 2×
“Alternatively, gradient projection can also be performed without storing old training samples [51], [65], [66], [67].”
BackgroundMnemonics Training: Multi-Class Incremental Learning Without Forgetting
Liu, Y., Su, Y., Liu, A.-A., Schiele, B., & Sun, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01226 · Cited by 309 · cited 1×
“Besides, the old training samples can be continually adjusted to accommodate incremental changes, e.g., making them more representative [143] or challenging [144] for separation.”
BackgroundSLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
Zhang, G., Wang, L., Kang, G., Chen, L., & Wei, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01754 · Cited by 308 · cited 3×
“SLCA [504] observes that slowly fine-tuning the backbone of a pre-trained transformer can achieve outstanding performance in continual learning, and further”
BackgroundSelf-citationThe Persistence and Transience of Memory
Richards, B. A., & Frankland, P. W. (2017) · Neuron · doi:10.1016/j.neuron.2017.04.037 · Cited by 305
Dopaminergic neurons write and update memories with cell-type-specific rules
Aso, Y., & Rubin, G. M. (2016) · eLife · doi:10.7554/elife.16135 · Cited by 304
IL2M: Class Incremental Learning With Dual Memory
Belouadah, E., & Popescu, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00067 · Cited by 302 · cited 3×
“IL2M [140] and SNCL [79] recover statistics of feature representations (e.g., mean and covariance) on the basis of experience replay.”
BackgroundA Deep Hierarchical Approach to Lifelong Learning in Minecraft
Tessler, C., Givony, S., Zahavy, T., Mankowitz, D., & Mannor, S. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10744 · Cited by 299
On Tiny Episodic Memories in Continual Learning
Chaudhry, A., Rohrbach, M., Elhoseiny, M., Ajanthan, T., Dokania, P. K., Torr, P. H. S., & Ranzato, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.10486 · Cited by 298
FearNet: Brain-Inspired Model for Incremental Learning
Kemker, R., & Kanan, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10563 · Cited by 296 · cited 4×
“In contrast, autoencoder-based strategies, such as FearNet [210], SRM [361], CLEER [366], EEC [26], GMR [334] and Flashcards [138], can explicitly control the labels of the generated data, although relatively blurred.”
BackgroundMethodInfluentialSelf-Supervised Models are Continual Learners
Fini, E., da Costa, V. G. T., Alameda-Pineda, X., Ricci, E., Alahari, K., & Mairal, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00940 · Cited by 288 · cited 1×
“CaSSLe [195] converts the self-supervised loss to a distillation strategy by mapping the current state of a representation to its previous state.”
BackgroundZhou, X., Wang, D., & Krähenbühl, P. (2019) · arXiv · doi:10.48550/arxiv.1904.07850 · Cited by 288 · cited 1×
“The idea of knowledge distillation is then introduced to other detection frameworks, such as CenterNet [508] (SID [328]), RetinaNet [259] (RILOD [247]), GFLV1 [250] (ERD [114]) and Faster R-CNN [358] (CIFRCN [152], Faster ILOD [327], DMC [493], BNC [96], IOD-ML [222]).”
MethodLearning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
Ostapenko, O., Puscas, M., Klein, T., Jähnichen, P., & Nabi, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01158 · Cited by 283 · cited 3×
“A majority of state-of-the-art approaches have focused on GANs to enjoy its advantages in fine-grained generation, but usually suffer from label inconsistency in continual learning [164], [168].”
BackgroundForward Compatible Few-Shot Class-Incremental Learning
Zhou, D.-W., Wang, F.-Y., Ye, H.-J., Ma, L., Pu, S., & Zhan, D.-C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00884 · Cited by 281 · cited 2×
“To promote learning plasticity on the basis of memory stability, emergent strategies include renormalization of the old and new task solutions [163], [255], [373], [429], balanced exploitation of the old and new training samples [11], [164], [171], [440], [457], [500], reserving space for subsequent tasks [10], [195],…”
BackgroundMethodMnemonics Training: Multi-Class Incremental Learning Without Forgetting
LIU, Y., SU, Y., LIU, A.-A., Schiele, B., & SUN, Q. (2020) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · Cited by 278
Progress & Compress: A scalable framework for continual learning
Schwarz, J., Luketina, J., Czarnecki, W. M., Grabska‐Barwińska, A., Teh, Y. W., Pascanu, R., & Hadsell, R. T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06370 · Cited by 272 · cited 3×
“The importance can be calculated by the Fisher information matrix (FIM), such as EWC [49] and some more advanced versions [50], [104].”
MethodMeta-Learning Representations for Continual LearningPreprint
Javed, K., & White, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.12588 · Cited by 270 · cited 4×
“AIM[183]learnsamixtureofexpertstomakepredic-tionswiththerepresentationsofOML[181]orANML[182], furthersparsifyingtherepresentationsatthearchitecturallevel.”
BackgroundInfluentialREMIND Your Neural Network to Prevent Catastrophic Forgetting
Hayes, T. L., Kafle, K., Shrestha, R., Acharya, M., & Kanan, C. (2019) · arXiv · doi:10.48550/arxiv.1910.02509 · Cited by 268
PLOP: Learning without Forgetting for Continual Semantic Segmentation
Douillard, A., Chen, Y., Dapogny, A., & Cord, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00403 · Cited by 267
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
Liu, X., Masana, M., Herranz, L., Van de Weijer, J., Lopez, A. M., & Bagdanov, A. D. (2018) · 2018 24th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr.2018.8545895 · Cited by 259
Incremental Learning Techniques for Semantic Segmentation
Michieli, U., & Zanuttigh, P. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00400 · Cited by 256
Overcoming Catastrophic Forgetting by Incremental Moment Matching
Lee, S.-W., Kim, J.-H., Jun, J., Ha, J.-W., & Zhang, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.08475 · Cited by 255 · cited 1×
“IMM [111] is an early attempt that incrementally matches the moment of the posterior distributions for old and new tasks, i.e., a weighted average of their solutions.”
BackgroundLoss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Garipov, T., Izmailov, P., Podoprikhin, D., Vetrov, D., & Wilson, A. G. (2018) · arXiv · doi:10.48550/arxiv.1802.10026 · Cited by 252 · cited 1×
“, integrating multiple minima in parameter or function space along the low-error path, since connecting them ensures flatness on that path [59], [129], [182], [308], [430], [450].”
BackgroundFlesch, T., Juechems, K., Dumbalska, T., Saxe, A., & Summerfield, C. (2022) · Neuron · doi:10.1016/j.neuron.2022.01.005 · Cited by 249
REMIND Your Neural Network to Prevent Catastrophic Forgetting
Hayes, T. L., Kafle, K., Shrestha, R., Acharya, M., & Kanan, C. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58598-3_28 · Cited by 248
Online Continual Learning with Maximal Interfered RetrievalPreprint
Aljundi, R., Belilovsky, E., Tuytelaars, T., Charlin, L., Caccia, M., Lin, M., & Caccia, L. (2019) · arXiv (Cornell University) · Cited by 245
Memory-Efficient Incremental Learning Through Feature Adaptation
İşcen, A., Zhang, J., Lazebnik, S., & Schmid, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58517-4_41 · Cited by 241
New Insights on Reducing Abrupt Representation Change in Online Continual LearningPreprint
Caccia, L., Aljundi, R., Asadi, N., Tuytelaars, T., Pineau, J., & Belilovsky, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.05025 · Cited by 237 · cited 1×
“…performing knowledge distillation [31], [278], improving representations with contrastive learning [276], [279], using asymmetric cross-entropy [280] or constrained gradient directions [45], [63] of the old new training samples, repeated rehearsal with data augmentation [281], properly…”
BackgroundBiological underpinnings for lifelong learning machines
Kudithipudi, D., Aguilar-Simon, M., Babb, J., Bazhenov, M., Blackiston, D., Bongard, J., Brna, A. P., Chakravarthi Raja, S., Cheney, N., Clune, J., et al. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00452-0 · Cited by 236 · cited 4×
“In contrast, the latest surveystypicallycollateonlyalocalaspectofcontinuallearning, withrespecttoitsbiologicalunderpinnings[1],[3],[9],[10], specializedsettingsforvisualclassification[11],[12],[13],[14], andspecificextensionsforNLP[15],[16]orRL[17].”
BackgroundInfluentialFederated Class-Incremental Learning
Dong, J., Wang, L., Fang, Z., Sun, G., Xu, S., Wang, X., & Zhu, Q. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00992 · Cited by 233 · cited 1×
“GLFC [95] overcomes catastrophic forgetting through knowledge distillation of a few old training samples, and alleviates class imbalance through gradient compensation.”
BackgroundSelf-citationGCR: Gradient Coreset based Replay Buffer Selection for Continual Learning
Tiwari, R., Killamsetty, K., Iyer, R., & Shenoy, P. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00020 · Cited by 227
Towards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2020) · arXiv · doi:10.48550/arxiv.2012.13490 · Cited by 227
Geometry of sequence working memory in macaque prefrontal cortex
Xie, Y., Hu, P., Li, J., Chen, J., Song, W., Wang, X.-J., Yang, T., Dehaene, S., Tang, S., Min, B., et al. (2022) · Science · doi:10.1126/science.abm0204 · Cited by 225
Self-citationTowards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13673 · Cited by 224
Class-Incremental Continual Learning Into the eXtended DER-Verse
Boschini, M., Bonicelli, L., Buzzega, P., Porrello, A., & Calderara, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206549 · Cited by 224
Re-evaluating Circuit Mechanisms Underlying Pattern Separation
Cayco-Gajic, N. A., & Silver, R. A. (2019) · Neuron · doi:10.1016/j.neuron.2019.01.044 · Cited by 222
Co2L: Contrastive Continual Learning
Cha, H., Lee, J., & Shin, J. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00938 · Cited by 215 · cited 4×
“Co2L [92] adopts a supervised contrastive loss to learn each task and a self-supervised loss to distill knowledge between the old and new models.”
BackgroundInfluentialCatastrophic forgetting and mode collapse in GANs
Thanh-Tung, H., & Tran, T. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207181 · Cited by 214 · cited 1×
“Similarly, resolving within-task catastrophic forgetting can facilitate reinforcement learning [299], [300] and stabilize the training of GANs [301], [302].”
BackgroundMichieli, U., & Zanuttigh, P. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00117 · Cited by 213 · cited 1×
“SDR [291] introduces contrastive learning into distillation of latent representations, where pixels of the same class are clustered and pixels of different classes are separated.”
BackgroundOvercoming catastrophic forgetting with hard attention to the task
Serrà, J., Surís, D., Miron, M., & Karatzoglou, A. (2018) · arXiv · doi:10.48550/arxiv.1801.01423 · Cited by 213
Scalable and Order-robust Continual Learning with Additive Parameter DecompositionPreprint
Yoon, J., Kim, S., Yang, E., & Hwang, S. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.09432 · Cited by 212 · cited 1×
“Besides, the network parameters themselves can be decomposed into task-sharing and task-specific elements, such as by additive decomposition (APD [479]), singular value decomposition (RCM [197]), filter atom decomposition (FAS [300]) and lowrank factorization (IBP-WF [294], IRU [177]).”
BackgroundRe-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
Hsu, Y.-C., Liu, Y.-C., Ramasamy, A., & Kira, Z. (2018) · arXiv · doi:10.48550/arxiv.1810.12488 · Cited by 211 · cited 15×
“CIL [169], [425] {Dt, t}t∈T ; p(Xi) ̸= p(Xj) and Yi ∩ Yj = ∅ for i ̸= j {p(Xt)}t∈T ; t is unavailable”
BackgroundInfluentialClass-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation
Kang, M., Park, J., & Han, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01560 · Cited by 207
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat MinimaPreprint
Shi, G., Chen, J., Zhang, W., Zhan, L.-M., & Wu, X.-M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.01549 · Cited by 206 · cited 6×
“As for optimizing an updatable backbone, F2M [389] searches for flat local minima in the pre-training stage, and then learns incremental tasks within the flat region.”
BackgroundInfluentialOvercoming Catastrophic Forgetting With Unlabeled Data in the Wild
Lee, K., Lee, K., Shin, J., & Lee, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00040 · Cited by 203 · cited 3×
“GD [124] further distills knowledge on the large stream of unlabeled data available in the wild.”
BackgroundSemantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Cheraghian, A., Rahman, S., Fang, P., Roy, S. K., Petersson, L., & Harandi, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00256 · Cited by 201 · cited 1×
“Besides, auxiliary information such as semantic word vectors [262], [263] and sketch exemplars [264] can be incorporated to enrich the limited training samples.”
BackgroundActivity-dependent gating of lateral inhibition in the mouse olfactory bulb
Arevian, A. C., Kapoor, V., & Urban, N. N. (2008) · Nature Neuroscience · doi:10.1038/nn2030 · Cited by 200
RECALL: Replay-based Continual Learning in Semantic Segmentation
Maracani, A., Michieli, U., Toldo, M., & Zanuttigh, P. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00694 · Cited by 199 · cited 2×
“PLOP [292], RECALL [293], SSUL [294], Self-Training [295] and WILSON [296] explicitly apply the old model to generate pseudo-labels of the old classes.”
BackgroundMethodContinual Prototype Evolution: Learning Online from Non-Stationary Data Streams
De Lange, M., & Tuytelaars, T. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00814 · Cited by 194 · cited 3×
“More advanced strategies prioritize the replay of those training samples that are informative (InfoRS [398]), diversified in parameter gradients (GSS [17]) or previously-learned knowledge (ODDL [473]), balanced in class labels (CBRS [75], GDumb [340], CoPE [86]), and beneficial to latent decision boundaries (ASER [382…”
BackgroundMethodRepresentation Compensation Networks for Continual Semantic Segmentation
Zhang, C., Xiao, J.-W., Liu, X., Chen, Y.-C., & Cheng, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00692 · Cited by 192 · cited 1×
“RCIL [290] reparameterizes the network into two parallel branches, where the old branch is frozen for KD between intermediate layers.”
BackgroundUsing Hindsight to Anchor Past Knowledge in Continual Learning
Chaudhry, A., Gordo, A., Dokania, P., Torr, P., & Lopez-Paz, D. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16861 · Cited by 191
Lifelong Learning via Progressive Distillation and Retrospection
Hou, S., Pan, X., Loy, C. C., Wang, Z., & Lin, D. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_27 · Cited by 190 · cited 3×
“To further enhance learning plasticity, D+R [154] performs KD from an additional model dedicated to each new task.”
BackgroundMethodOnline Class-Incremental Continual Learning with Adversarial Shapley Value
Shim, D., Mai, Z., Jeong, J., Sanner, S., Kim, H., & Jang, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17159 · Cited by 189 · cited 2×
“More advanced strategies prioritize the replay of those training samples that are informative [273], diversified in parameter gradients [21], balanced in class labels [159], [274], and beneficial to latent decision boundaries [134].”
BackgroundUncertainty-guided Continual Learning with Bayesian Neural NetworksPreprint
Ebrahimi, S., Elhoseiny, M., Darrell, T., & Rohrbach, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02425 · Cited by 189 · cited 1×
“Except for the TIL setting that always provides the task identity I D t [70], [71], [72], [73], other scenarios generally require the model to determine which θ ( t ) to use based on the input data, as shown in (10).”
MethodContinual Learning with Node-Importance based Adaptive Group Sparse RegularizationPreprint
Jung, S., Ahn, H., Cha, S., & Moon, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13726 · Cited by 186 · cited 7×
“UCL [115] and AGS-CL [116] freeze the parameters connecting the important neurons, equivalent to a hard version of weight regularization.”
BackgroundInfluentialXu, J., & Zhu, Z. (2018) · ePrints Soton (University of Southampton) · doi:10.48550/arxiv.1805.12369 · Cited by 185 · cited 1×
“The dynamic architecture can be explicitly optimized to improve parameter efficiency and knowledge transfer, such as by reinforcement learning [229], [230], architecture search [230], [231], variational Bayes [232], etc.”
BackgroundSide-Tuning: A Baseline for Network Adaptation via Additive Side Networks
Zhang, J. O., Sax, A., Zamir, A., Guibas, L., & Malik, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58580-8_41 · Cited by 184 · cited 1×
“As for adapting a fixed backbone, Side-Tuning [198] and DLCFT [199] train a lightweight network in parallel with the backbone and fuse their outputs linearly.”
MethodFaster ILOD: Incremental learning for object detectors based on faster RCNN
Peng, C., Zhao, K., & Lovell, B. C. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.09.030 · Cited by 183
What is being transferred in transfer learning?
Neyshabur, B., Sedghi, H., & Zhang, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.11687 · Cited by 183 · cited 1×
“Empirically, both can be attributed to obtaining a more robust representation [28], [89], [93], [191], and converging to a wider loss basin [28], [87], [93], [192], [193], suggesting a potential link among the sensitivity of representations, parameters and task-specific errors.”
BackgroundHierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Wang, L., Xie, J., Zhang, X., et al. (2023) · Neural Information Processing Systems · doi:10.48550/arxiv.2310.07234 · Cited by 183
Self-citationMai, Z., Li, R., Kim, H., & Sanner, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00398 · Cited by 181 · cited 2×
“OCL InstAParam [68], CBRS [75], ASER [382], InfoRS [398], DVC [143], CTN [336], NCCL [475], ILOS [158], SCR [284], CVT [441], OCM [145], ER-ACE [47], RAR [498], PoLRS [50], AOP [144], CV [159]”
BackgroundMethodIncremental Object Detection via Meta-Learning
Joseph, K. J., Rajasegaran, J., Khan, S. H., Khan, F. S., & Balasubramanian, V. N. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3124133 · Cited by 180 · cited 3×
“To further mitigate the negative effects of knowledge distillation on learning plasticity, IOD-ML [222] adopts meta-learning to reshape parameter gradients into a balanced direction between the old and new classes.”
MethodSelf-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
Zhu, K., Cao, Y., Zhai, W., Cheng, J., & Zha, Z.-J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00673 · Cited by 179 · cited 1×
“Under this framework, representative strategies can be conceptually separated into (1) obtaining compatible and extensible representations from the base classes, such as by enforcing the representations compatible with simulated incremental tasks (SPPR [511], LIMIT [505]), reserving the”
MethodSelf-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning
Zhu, K., Zhai, W., Cao, Y., Luo, J., & Zha, Z.-J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00908 · Cited by 179 · cited 3×
“Other methods exploit the class-wise statistics of feature representations to obtain a balanced classifier, such as by imposing the representations to be transferable and invariant (SPB [453], IL2A [509], SSRE [512], FeTrIL [333]), or compensating explicitly the representation shifts (SDC [484], RER [409]).”
MethodSS-IL: Separated Softmax for Incremental Learning
Ahn, H., Kwak, J., Lim, S., Bang, H., Kim, H., & Moon, T. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00088 · Cited by 177 · cited 2×
“…tasksolutions[52],[104],[113],[154],[196],balancedexploita-tionofoldandnewtrainingsamples[46],[129],[147],[148], [149],[152],spacereservationforsubsequenttasks[115],[116], [256],etc. Ontheotherhand,solutiongeneralizabilitycould…”
Lifelong GAN: Continual Learning for Conditional Image Generation
Zhai, M., Chen, L., Tung, F., He, J., Nawhal, M., & Mori, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00285 · Cited by 175 · cited 2×
“For conditional generation, the generated data of previously-learned conditions and their output values are regularized to be consistent between the teacher and student models, such as MeRGANs [125], DRI [129] and LifelongGAN [126].”
BackgroundIncremental Learning Using Conditional Adversarial Networks
Xiang, Y., Fu, Y., Ji, P., & Huang, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00672 · Cited by 175 · cited 2×
“For example, FearNet [210] and ILCAN [461] additionally preserves statistical information of the old features acquired from a pre-trained feature extractor, while GAN-Memory [80] continually adjusts a pre-trained generative model with taskspecific parameters.”
BackgroundIncremental Learning in Online Scenario
He, J., Mao, R., Shao, Z., & Zhu, F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01394 · Cited by 173
Espinoza, C., Guzman, S. J., Zhang, X., & Jonas, P. (2018) · Nature Communications · doi:10.1038/s41467-018-06899-3 · Cited by 173
Self-citationConditional Channel Gated Networks for Task-Aware Continual Learning
Abati, D., Tomczak, J., Blankevoort, T., Calderara, S., Cucchiara, R., & Bejnordi, B. E. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00399 · Cited by 171
Online Coreset Selection for Rehearsal-based Continual LearningPreprint
Yoon, J., Madaan, D., Yang, E., & Hwang, S. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01085 · Cited by 171 · cited 1×
“…[21], performance of corresponding tasks with cardinality constraints [132], mini-batch gradient similarity and cross-batch gradient diversity [133], ability of optimizing latent decision boundaries [134], diversity of robustness against perturbations [32], similarity to the gradients of old…”
BackgroundContinual Federated Learning Based on Knowledge Distillation
Ma, Y., Xie, Z., Wang, J., Chen, K., & Shou, L. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/303 · Cited by 170 · cited 1×
“…data collected by clients is dynamic and variable, federated learning needs to overcome catastrophic forgetting and facilitate knowledge transfer across clients, which can be achieved by continual learning strategies such as model decomposition [304] and knowledge distillation [305], [306].”
BackgroundLifelong Learning with Dynamically Expandable Networks
Yoon, J., Yang, E., Lee, J., & Hwang, S. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.01547 · Cited by 168 · cited 1×
“To alleviate this dilemma, the network architecture can be dynamically expanded if its capacity is not sufficient to learn a new task well, such as DEN [481], CPG [174] and DGMa/DGMw [317].”
BackgroundDistilling Causal Effect of Data in Class-Incremental Learning
Hu, X., Tang, K., Miao, C., Hua, X.-S., & Zhang, H. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00395 · Cited by 167 · cited 5×
“In this regard, replay of the old training samples is able to impose an end-to-end effect, while feature and label distillations of the new training samples are limited to the output side with a biased distribution [171].”
BackgroundMethodInfluentialConstrained Few-shot Class-incremental Learning
Hersche, M., Karunaratne, G., Cherubini, G., Benini, L., Sebastian, A., & Rahimi, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00885 · Cited by 167 · cited 1×
“…extraconstraintsfrommargin-basedrepresentations[258],etc. Thesecondistoobtainanadaptiveclassifierfromasequence of novel classes, such as by evolving the classifier weights with a graph attention network [259], performing hyperdimen-sional computing [260], sampling stochastic classifiers [261], etc.”
Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
Liu, H., Gu, L., Chi, Z., Wang, Y., Yu, Y., Chen, J., & Tang, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20053-3_9 · Cited by 167
Visualizing and Understanding the Effectiveness of BERT
Hao, Y., Dong, L., Wei, F., & Xu, K. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1424 · Cited by 166 · cited 1×
“, orthogonal, sparse and uniformly-scattered) representation [167], [281], [352], [380], and converging to a wider loss basin [151], [167], [281], [295], [313], suggesting a potential link among the sensitivity of representations, parameters and task-specific errors.”
BackgroundMetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning
Chi, Z., Gu, L., Liu, H., Wang, Y., Yu, Y., & Tang, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01377 · Cited by 164 · cited 1×
“…graph for knowledge distillation [250], selectively updating only the unimportant parameters [251] or stabilizing the important parameters [252], updating parameters within the flat region of loss landscape [84], meta-learning of a good initialization [253], as well as generative replay [254].”
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
Ritter, H., Botev, A., & Barber, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07810 · Cited by 164 · cited 3×
“diagonal approximation [179], [227] or a Kronecker-factored approximation [296], [373].”
InfluentialMemory Replay with Data Compression for Continual LearningPreprint
Wang, L., Zhang, X., Yang, K., Yu, L., Li, C., Hong, L., Zhang, S., Li, Z., Zhong, Y., & Zhu, J. J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.06592 · Cited by 164 · cited 1×
“MRDC [138] formulates experience replay with data compression as determinantal point processes (DPPs), and derives a computationally efficient way for online determination of the optimal compression rate.”
Self-citationAdversarial Continual Learning
Ebrahimi, S., Meier, F., Calandra, R., Darrell, T., & Rohrbach, M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_23 · Cited by 162
Topology-Preserving Class-Incremental Learning
Tao, X., Chang, X., Hong, X., Wei, X., & Gong, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58529-7_16 · Cited by 162 · cited 2×
“Data Space iCaRL [356], GSS [17], Mnemonics [272], TPCIL [403], GDumb [340], DER++ [46], RMM [271], HAL [63], MRDC [431], CSI [217], X-DER [41]”
MethodFew-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
Zhou, D.-W., Ye, H.-J., Ma, L., Xie, D., Pu, S., & Zhan, D.-C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3200865 · Cited by 162
Few-Shot Class-Incremental Learning via Relation Knowledge Distillation
Dong, S., Hong, X., Tao, X., Chang, X., Wei, X., & Gong, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16213 · Cited by 161 · cited 1×
“The extremely limited training samples exacerbate the overfitting of previously-learned representations to subsequent tasks, which can be alleviated by recent work such as preserving the topology of representations (TOPIC [404]), constructing an exemplar relation graph for knowledge distillation (ERL [97]), selectivel…”
BackgroundFeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
Petit, G., Popescu, A., Schindler, H., Picard, D., & Delezoide, B. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00390 · Cited by 161 · cited 3×
“Other methods exploit the class-wise statistics of feature representations to obtain a balanced classifier, such as by imposing the representations to be transferable and invariant (SPB [453], IL2A [509], SSRE [512], FeTrIL [333]), or compensating explicitly the representation shifts (SDC [484], RER [409]).”
BackgroundMethodLinear Mode Connectivity in Multitask and Continual LearningPreprint
Mirzadeh, S. I., Farajtabar, M., Görür, D., Pascanu, R., & Ghasemzadeh, H. G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04495 · Cited by 161 · cited 6×
“MC-SGD [308] empirically demonstrates that the local minima obtained by multi-task learning (i.”
BackgroundMethodInfluentialOnline Fast Adaptation and Knowledge Accumulation: a New Approach to Continual LearningPreprint
Caccia, M., Rodríguez, P., Ostapenko, O., Normandin, F., Lin, M., Caccia, L., Laradji, I., Rish, I., Lacoste, A., Vázquez, D., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.05856 · Cited by 160
Imbalanced Continual Learning with Partitioning Reservoir Sampling
Kim, C. D., Jeong, J., & Kim, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58601-0_25 · Cited by 155
Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning
Smith, J., Hsu, Y.-C., Balloch, J., Shen, Y., Jin, H., & Kira, Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00924 · Cited by 155 · cited 1×
“An intriguing idea is to replay synthetic data produced by inverting a frozen copy of the old classification model [247], [248], which usually further incorporate knowledge distillation to compensate the lost information in model inversion.”
BackgroundCompacting, Picking and Growing for Unforgetting Continual Learning
Hung, S. C. Y., Tu, C.-H., Wu, C.-E. R., Chen, C., Chan, Y.-M., & Chen, C.-S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.06562 · Cited by 154 · cited 1×
“Toalleviatethisdilemma, thenetworkarchitecturecanbe dynamically expanded if its capacity is not sufficient to learn a new task well [164], [227], [228].”
BackgroundOngoing in Vivo Experience Triggers Synaptic Metaplasticity in the Neocortex
Clem, R. L., Celikel, T., & Barth, A. L. (2008) · Science · doi:10.1126/science.1143808 · Cited by 151
Recent Advances of Continual Learning in Computer Vision: An Overview
Qu, H., Rahmani, H., Xu, L., Williams, B. M., & Liu, J. (2025) · IET Computer Vision · doi:10.1049/cvi2.70013 · Cited by 142
A Theoretical Study on Solving Continual Learning
Kim, G., Xiao, C., Konishi, T., Ke, Z., & Liu, B. (2022) · neural information processing systems · doi:10.52202/068431-0366 · Cited by 142
Gradient-based Editing of Memory Examples for Online Task-free Continual LearningPreprint
Jin, X., Sadhu, A., Du, J., & Ren, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.15294 · Cited by 137 · cited 2×
“Besides, the old training samples can be continually adjusted to accommodate incremental changes, e.g., making them more representative [143] or challenging [144] for separation.”
BackgroundRepresentational Continuity for Unsupervised Continual LearningPreprint
Madaan, D., Yoon, J., Li, Y., Liu, Y., & Hwang, S. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.06976 · Cited by 137 · cited 10×
“Observing that self-supervised representations are more robust to catastrophic forgetting, LUMP [93] acquires further improvements by interpolating between instances of the old and new tasks.”
BackgroundMethodInfluentialiTAML: An Incremental Task-Agnostic Meta-learning Approach
Rajasegaran, J., Khan, S., Hayat, M., Khan, F. S., & Shah, M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01360 · Cited by 136
Gu, Y., Yang, X., Wei, K., & Deng, C. D. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00729 · Cited by 136 · cited 3×
“Meanwhile, the memory buffer can be dynamically managed, such as by removing less important training samples (CLIB [224]), editing the old training samples (GMED [191]) or their distributions (DRO [443]) to be more likely forgotten, and retrieving the old training samples that are susceptible to interference (MIR [14]…”
BackgroundMethodCORe50: a New Dataset and Benchmark for Continuous Object Recognition
Lomonaco, V., & Maltoni, D. (2017) · arXiv · doi:10.48550/arxiv.1705.03550 · Cited by 135
Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
Feng, T., Wang, M., & Yuan, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00921 · Cited by 132 · cited 1×
“The idea of knowledge distillation is then introduced to other detection frameworks [283], [284], [285].”
MethodMundt, M., Hong, Y., Pliushch, I., & Ramesh, V. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.014 · Cited by 132
Continual Lifelong Learning in Natural Language Processing: A Survey
Biesialska, M., Biesialska, K., & Costa-jussà, M. R. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.574 · Cited by 131 · cited 1×
“In contrast, the latest surveystypicallycollateonlyalocalaspectofcontinuallearning, withrespecttoitsbiologicalunderpinnings[1],[3],[9],[10], specializedsettingsforvisualclassification[11],[12],[13],[14], andspecificextensionsforNLP[15],[16]orRL[17].”
Anatomy of Catastrophic Forgetting: Hidden Representations and Task SemanticsPreprint
Ramasesh, V., Dyer, E., & Raghu, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.07400 · Cited by 131
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap MatrixPreprint
Doan, T., Bennani, M., Mazoure, B., Rabusseau, G., & Alquier, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04003 · Cited by 130 · cited 1×
“Sometheoreticalstudieswiththeneuraltangent kernel (NTK) [96], [97], [98], [99] suggest that an increase in task similarity may lead to more forgetting.”
BackgroundGradient Projection Memory for Continual Learning
Saha, G., Garg, I., & Roy, K. (2021) · arXiv · doi:10.48550/arxiv.2103.09762 · Cited by 129 · cited 3×
“Theauxiliaryinformationwithlowstoragecost,suchasclass statistics[79],[140]andattentionmaps[141],[142],canbe further incorporated to maintain old knowledge.”
BackgroundThe Turking Test: Can Language Models Understand Instructions?Preprint
Efrat, A., & Levy, O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.11982 · Cited by 128
Co-Transport for Class-Incremental Learning
Zhou, D.-W., Ye, H.-J., & Zhan, D. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475306 · Cited by 127
Research works printed but not linked: 96
- Elahe Arani, Fahad Sarfraz, and Bahram Zonooz. Learning fast, learning slow: A general continual learning method based on complementary learning system. In International Conference on Learning Representations, 2021.
- Dushyant Rao, Francesco Visin, Andrei Rusu, Razvan Pascanu, Yee Whye Teh, and Raia Hadsell. Continual unsupervised rep- resentation learning. Advances in Neural Information Processing Systems, 32, 2019.
- Fan Bao, Chongxuan Li, Jun Zhu, and Bo Zhang. Analytic- dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models. In International Conference on Learning Representations, 2021.
- Wickliffe C Abraham. Metaplasticity: tuning synapses and net- works for plasticity. Nature Reviews Neuroscience, 9(5):387-387, 2008.
- Alessandro Achille, Tom Eccles, Loic Matthey, Chris Burgess, Nicholas Watters, Alexander Lerchner, and Irina Higgins. Life- long disentangled representation learning with cross-domain latent homologies. Advances in Neural Information Processing Systems, 31, 2018.
- Idan Achituve, Aviv Navon, Yochai Yemini, Gal Chechik, and Ethan Fetaya. Gp-tree: A gaussian process classifier for few- shot incremental learning. In International Conference on Machine Learning, pages 54-65. PMLR, 2021.
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929-1958, 2014.
- Serban Stan and Mohammad Rostami. Unsupervised model adaptation for continual semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 2593-2601, 2021.
- Fan-Keng Sun, Cheng-Hao Ho, and Hung-Yi Lee. Lamol: Lan- guage modeling for lifelong language learning. In International Conference on Learning Representations, 2019.
- Jingyuan Sun, Shaonan Wang, Jiajun Zhang, and Chengqing Zong. Distill and replay for continual language learning. In Proceedings of the 28th international conference on computational linguistics, pages 3569-3579, 2020.
- Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. In Advances in Neural Information Processing Systems, 2022.
- Akiko Hayashi-Takagi, Sho Yagishita, Mayumi Nakamura, Fuku- toshi Shirai, Yi I Wu, Amanda L Loshbaugh, Brian Kuhlman, Klaus M Hahn, and Haruo Kasai. Labelling and optical era- sure of synaptic memory traces in the motor cortex. Nature, 525(7569):333-338, 2015.
- David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lil- licrap, and Gregory Wayne. Experience replay for continual learning. Advances in Neural Information Processing Systems, 32, 2019.
- Mohammad Rostami, Soheil Kolouri, Praveen Pilly, and James McClelland. Generative continual concept learning. In Proceed- ings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5545-5552, 2020.
- Mohammad Rostami, Soheil Kolouri, and Praveen K Pilly. Com- plementary learning for overcoming catastrophic forgetting us- ing experience replay. In Proceedings of the International Joint Conference on Artificial Intelligence, pages 3339-3345, 2019.
- Aishwarya Agarwal, Biplab Banerjee, Fabio Cuzzolin, and Sub- hasis Chaudhuri. Semantics-driven generative replay for few- shot class incremental learning. In Proceedings of the ACM Inter- national Conference on Multimedia, pages 5246-5254, 2022.
- Ben Tsuda, Kay M Tye, Hava T Siegelmann, and Terrence J Sejnowski. A modeling framework for adaptive lifelong learning with transfer and savings through gating in the prefrontal cortex. Proceedings of the National Academy of Sciences, 117(47):29872- 29882, 2020.
- Weikang Wang, Jiajun Zhang, Qian Li, Mei-Yuh Hwang, Chengqing Zong, and Zhifei Li. Incremental learning from scratch for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3710-3720, 2019.
- Mehrab N Modi, Yichun Shuai, and Glenn C Turner. The drosophila mushroom body: From architecture to algorithm in a learning circuit. Annual Review of Neuroscience, 43:465-484, 2020.
- Natawut Monaikul, Giuseppe Castellucci, Simone Filice, and Oleg Rokhlenko. Continual learning for named entity recogni- tion. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13570-13577, 2021.
- Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron Courville, and Sarath Chandar. Continuous coordination as a realistic scenario for lifelong learning. In International Conference on Machine Learn- ing, pages 8016-8024. PMLR, 2021.
- Jorge Mendez, Boyu Wang, and Eric Eaton. Lifelong policy gradient learning of factored policies for faster training without forgetting. Advances in Neural Information Processing Systems, 33:14398-14409, 2020.
- Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang, and Boi Faltings. Continual learning for natural language generation in task-oriented dialog systems. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3461-3474, 2020.
- Vinay Venkatesh Ramasesh, Aitor Lewkowycz, and Ethan Dyer. Effect of scale on catastrophic forgetting in neural networks. In International Conference on Learning Representations, 2021.
- Seyed Iman Mirzadeh, Mehrdad Farajtabar, and Hassan Ghasemzadeh. Dropout as an implicit gating mechanism for continual learning. In CVPR Workshops, pages 232-233, 2020.
- Junbum Cha, Sanghyuk Chun, Kyungjae Lee, Han-Cheol Cho, Seunghyun Park, Yunsung Lee, and Sungrae Park. Swad: Do- main generalization by seeking flat minima. Advances in Neural Information Processing Systems, 34:22405-22418, 2021.
- Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul A Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Pascale Fung, and Zhiguang Wang. Continual learning in task-oriented dialogue systems. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7452-7467, 2021.
- Maciej Wolczyk, Michal Zajkac, Razvan Pascanu, Lukasz Kucin- ski, and Piotr Milos. Continual world: A robotic benchmark for continual reinforcement learning. Advances in Neural Information Processing Systems, 34:28496-28510, 2021.
- Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Re- becca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In Interna- tional Conference on Machine Learning, pages 23965-23998. PMLR, 2022.
- Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Anirud- dha Kembhavi, Mohammad Rastegari, Jason Yosinski, and Ali Farhadi. Supermasks in superposition. Advances in Neural Information Processing Systems, 33:15173-15184, 2020.
- Frederik Benzing. Unifying importance based regularisation methods for continual learning. In International Conference on Artificial Intelligence and Statistics, pages 2372-2396. PMLR, 2022.
- Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn, and Sergey Levine. Comps: Continual meta policy search. In Interna- tional Conference on Learning Representations, 2021.
- Prashant Shivaram Bhat, Bahram Zonooz, and Elahe Arani. Task- aware information routing from common representation space in lifelong learning. In International Conference on Learning Represen- tations, 2023.
- Jaeyoo Park, Minsoo Kang, and Bohyung Han. Class-incremental learning for action recognition in videos. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13698-13707, 2021.
- Ramakanth Pasunuru, Veselin Stoyanov, and Mohit Bansal. Con- tinual few-shot learning for text classification. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5688-5702, 2021.
- Dingcheng Li, Zheng Chen, Eunah Cho, Jie Hao, Xiaohu Liu, Fan Xing, Chenlei Guo, and Yang Liu. Overcoming catastrophic forgetting during domain adaptation of seq2seq language gener- ation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5441-5454, 2022.
- Dawei Li, Serafettin Tasci, Shalini Ghosh, Jingwen Zhu, Junting Zhang, and Larry Heck. Rilod: Near real-time incremental learning for object detection at the edge. In Proceedings of the 4th ACM/IEEE Symposium on Edge Computing, pages 113-126, 2019.
- Guodun Li, Yuchen Zhai, Qianglong Chen, Xing Gao, Ji Zhang, and Yin Zhang. Continual few-shot intent detection. In Proceed- ings of the 29th International Conference on Computational Linguis- tics, pages 333-343, 2022.
- Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in hetero- geneous networks. Proceedings of Machine Learning and Systems, 2:429-450, 2020.
- Shuhao Gu and Yang Feng. Investigating catastrophic forgetting during continual training for neural machine translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4315-4326, 2020.
- Yanan Gu, Cheng Deng, and Kun Wei. Class-incremental instance segmentation via multi-teacher networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 1478- 1486, 2021.
- Zhuang Li, Lizhen Qu, and Gholamreza Haffari. Total recall: a customized continual learning method for neural semantic parsers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3816-3831, 2021.
- Haopeng Ren, Yi Cai, Xiaofeng Chen, Guohua Wang, and Qing Li. A two-phase prototypical network model for incremental few-shot relation classification. In Proceedings of the International Conference on Computational Linguistics, pages 1618-1629, 2020.
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 2015.
- Guile Wu, Shaogang Gong, and Pan Li. Striking a balance between stability and plasticity for class-incremental learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1124-1133, 2021.
- Tongtong Wu, Xuekai Li, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi, Yujin Zhu, and Guoqiang Xu. Curriculum-meta learn- ing for order-robust continual relation extraction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 10363-10369, 2021.
- Zhen Wang, Liu Liu, Yajing Kong, Jiaxian Guo, and Dacheng Tao. Online continual learning with contrastive vision transformer. In European Conference on Computer Vision, pages 631-650. Springer, 2022.
- Vaibhav Varshney, Mayur Patidar, Rajat Kumar, Lovekesh Vig, and Gautam Shroff. Prompt augmented generative replay via supervised contrastive learning for lifelong intent detection. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1113-1127, 2022.
- Qiu-Feng Wang, Xin Geng, Shu-Xia Lin, Shi-Yu Xia, Lei Qi, and Ning Xu. Learngene: From open-world to your learning task. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 8557-8565, 2022.
- Evgenii Egorov, Anna Kuzina, and Evgeny Burnaev. Boovae: Boosting approach for continual learning of vae. Advances in Neural Information Processing Systems, 34:17889-17901, 2021.
- Jonathan Schwarz, Daniel Altman, Andrew Dudzik, Oriol Vinyals, Yee Whye Teh, and Razvan Pascanu. Towards a natural benchmark for continual learning. In NeurIPS Workshops, 2018.
- Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10012-10022, 2021.
- Vincenzo Lomonaco, Karan Desai, Eugenio Culurciello, and Davide Maltoni. Continual reinforcement learning in 3d non- stationary environments. In CVPR Workshops, pages 248-249, 2020.
- Andrés Villa, Kumail Alhamoud, Victor Escorcia, Fabian Caba, Juan Le ón Alcázar, and Bernard Ghanem. vclimb: A novel video class incremental learning benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19035-19044, 2022.
- Jeffrey S Vitter. Random sampling with a reservoir. ACM Transactions on Mathematical Software (TOMS), 11(1):37-57, 1985.
- Johannes von Oswald, Christian Henning, Benjamin F Grewe, and João Sacramento. Continual learning with hypernetworks. In International Conference on Learning Representations, 2019.
- Scott Waddell. Neural plasticity: Dopamine tunes the mushroom body output network. Current Biology, 26(3):R109-R112, 2016.
- Chengyu Wang, Haojie Pan, Yuan Liu, Kehan Chen, Minghui Qiu, Wei Zhou, Jun Huang, Haiqing Chen, Wei Lin, and Deng Cai. Mell: Large-scale extensible user intent classification for dialogue systems with meta lifelong learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 3649-3659, 2021.
- Chen Wang, Yuheng Qiu, Dasong Gao, and Sebastian Scherer. Lifelong graph learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13719-13728, 2022.
- Yaoyao Liu, Bernt Schiele, and Qianru Sun. Adaptive aggregation networks for class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2544-2553, 2021.
- Yaoyao Liu, Bernt Schiele, and Qianru Sun. Rmm: Reinforced memory management for class-incremental learning. Advances in Neural Information Processing Systems, 34:3478-3490, 2021.
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Im- agenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems, volume 25, pages 1097-1105, 2012.
- Rui Wang, Tong Yu, Handong Zhao, Sungchul Kim, Subrata Mi- tra, Ruiyi Zhang, and Ricardo Henao. Few-shot class-incremental learning for named entity recognition. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 571-582, 2022.
- Christian Geishauser, Carel van Niekerk, Hsien-Chin Lin, Nurul Lubis, Michael Heck, Shutong Feng, and Milica Gasic. Dy- namic dialogue policy for continual reinforcement learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 266-284, 2022.
- Ross Girshick. Fast r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, pages 1440-1448, 2015.
- Yu Hao, Yanwei Fu, Yu-Gang Jiang, and Qi Tian. An end-to-end architecture for class-incremental object detection with knowl- edge distillation. In IEEE International Conference on Multimedia and Expo, pages 1-6. IEEE, 2019.
- Chengwei Qin and Shafiq Joty. Lfpt5: A unified framework for lifelong few-shot language learning based on prompt tuning of t5. In International Conference on Learning Representations, 2021.
- Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, and Manmohan Chandraker. On generalizing beyond domains in cross-domain continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9265-9274, 2022.
- Juan-Manuel Perez-Rua, Xiatian Zhu, Timothy M Hospedales, and Tao Xiang. Incremental few-shot object detection. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13846-13855, 2020.
- Khurram Javed and Martha White. Meta-learning represen- tations for continual learning. Advances in Neural Information Processing Systems, 32, 2019.
- Stan Franklin. Autonomous agents as embodied ai. Cybernetics & Systems, 28(6):499-520, 1997.
- Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. Mixup: Beyond empirical risk minimization. In International Conference on Learning Representations, 2018.
- Shipeng Yan, Jiangwei Xie, and Xuming He. Der: Dynamically expandable representation for class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3014-3023, 2021.
- Shipeng Yan, Jiale Zhou, Jiangwei Xie, Songyang Zhang, and Xuming He. An em framework for online incremental learning of semantic segmentation. In Proceedings of the ACM International Conference on Multimedia, pages 3052-3060, 2021.
- Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota, Mingli Ding, Moin Nabi, Xavier Alameda-Pineda, and Elisa Ricci. Uncertainty- aware contrastive distillation for incremental semantic segmenta- tion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
- Tianlin Liu, Lyle Ungar, and Joao Sedoc. Continual learning for sentence representations using conceptors. In Proceedings of NAACL-HLT, pages 3274-3279, 2019.
- Kelvin Xu, Siddharth Verma, Chelsea Finn, and Sergey Levine. Continual learning of control primitives: Skill discovery via reset- games. Advances in Neural Information Processing Systems, 33:4999- 5010, 2020.
- Mengqi Xue, Haofei Zhang, Jie Song, and Mingli Song. Meta- attention for vit-backed continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 150-159, 2022.
- Congying Xia, Wenpeng Yin, Yihao Feng, and S Yu Philip. Incremental few-shot text classification with multi-round new classes: Formulation, dataset and system. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1351-1360, 2021.
- Kenji Doya. Complementary roles of basal ganglia and cerebel- lum in learning and motor control. Current opinion in neurobiology, 10(6):732-739, 2000.
- Zichen Miao, Ze Wang, Wei Chen, and Qiang Qiu. Continual learning with filter atom swapping. In International Conference on Learning Representations, 2021.
- Sergey Ioffe and Christian Szegedy. Batch normalization: Ac- celerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, pages 448- 456. PMLR, 2015.
- Torben Ott and Andreas Nieder. Dopamine and cognitive control in prefrontal cortex. Trends in Cognitive Sciences, 23(3):213-234, 2019.
- Ron Chrisley. Embodied artificial intelligence. Artificial intelli- gence, 149(1):131-150, 2003.
- Aristotelis Chrysakis and Marie-Francine Moens. Online contin- ual learning from imbalanced data. In International Conference on Machine Learning, pages 1952-1961. PMLR, 2020.
- Randy Ardywibowo, Zepeng Huo, Zhangyang Wang, Bobak J Mortazavi, Shuai Huang, and Xiaoning Qian. Varigrow: Varia- tional architecture growing for task-agnostic continual learning based on bayesian novelty. In International Conference on Machine Learning, pages 865-877. PMLR, 2022.
- Pei Chen, Yangkang Zhang, Zejian Li, and Lingyun Sun. Few- shot incremental learning for label-to-image translation. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3697-3707, 2022.
- Yiduo Guo, Bing Liu, and Dongyan Zhao. Online continual learn- ing through mutual information maximization. In International Conference on Machine Learning, pages 8109-8126. PMLR, 2022.
- Mozhgan PourKeshavarzi, Guoying Zhao, and Mohammad Sabokrou. Looking back on learned experiences for class/task incremental learning. In International Conference on Learning Representations, 2021.
- Jiangpeng He and Fengqing Zhu. Online continual learning via candidates voting. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3154-3163, 2022.
- Haw-Shiuan Chang, Erik Learned-Miller, and Andrew McCal- lum. Active bias: Training more accurate neural networks by em- phasizing high variance samples. Advances in Neural Information Processing Systems, 30, 2017.
- Wenpeng Hu, Zhou Lin, Bing Liu, Chongyang Tao, Zhengwei Tao Tao, Dongyan Zhao, Jinwen Ma, and Rui Yan. Overcoming catas- trophic forgetting for continual learning via model adaptation. In International Conference on Learning Representations, 2019.
- Wenpeng Hu, Qi Qin, Mengyu Wang, Jinwen Ma, and Bing Liu. Continual learning by using information of each class holistically. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 7797-7805, 2021.
- Haiyan Yin, Ping Li, et al. Mitigating forgetting in online continual learning with neuron calibration. Advances in Neural Information Processing Systems, 34:10260-10272, 2021.
- Fei Zhu, Zhen Cheng, Xu-Yao Zhang, and Cheng-lin Liu. Class- incremental learning via dual augmentation. Advances in Neural Information Processing Systems, 34:14306-14318, 2021.
- Fei Zhu, Xu-Yao Zhang, Chuang Wang, Fei Yin, and Cheng-Lin Liu. Prototype augmentation and self-supervision for incremen- tal learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5871-5880, 2021.
Cited by
Atakishiyev, S., Salameh, M., Yao, H., & Goebel, R. (2024) · IEEE Access · doi:10.1109/access.2024.3431437 · Cited by 323
Atakishiyev, S., Salameh, M., Yao, H., & Goebel, R. (2021) · arXiv · doi:10.48550/arxiv.2112.11561 · Cited by 336
Vision-language models for medical report generation and visual question answering: a review
Hartsock, I., & Rasool, G. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1430984 · Cited by 229
A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Younesi, A., Ansari, M., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024) · IEEE Access · doi:10.1109/access.2024.3376441 · Cited by 197
“Models must avoid catastrophic forgetting when presented with new classes or shifts in existing class definitions without revisiting historical data [391], [392], [393], [394], [395], [396], [397], [398], [399], [400].”
BackgroundVoyager: An Open-Ended Embodied Agent with Large Language Models
Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., & Anandkumar, A. (2023) · arXiv · doi:10.48550/arxiv.2305.16291 · Cited by 222
“[32] Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu.”
Background
Metadata
- Authors
- Wang, L., Zhang, X., Su, H., & Zhu, J.
- Affiliations
- Tsinghua University (CN)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2024-08
- Volume
- 46
- Issue
- 8
- Pages
- 5362-5383
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4392173735
- Cited by
- 1,113
- References
- 313
- Citations by year
- 2026: 437 · 2025: 471 · 2024: 170
- FWCI
- 158.75
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62350080, 62076147, 62106123, U19A2081)
- BNRist (BNR2022RC01006)
- Tsinghua Institute for Guo Qiang
- Tsinghua-OPPO Joint Research Center for Future Terminal Technology
- High Performance Computing Center
- Tsinghua University
- Postdoctoral Fellowship Program of CPSF (GZB20230350)
- Shuimu Tsinghua Scholar
- New Cornerstone Science Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Data Stream Mining Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- continual learning, catastrophic forgetting, stability-plasticity trade-off, resource efficiency, incremental learning, adaptive intelligent systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.