A Continual Learning Survey: Defying Forgetting in Classification Tasks
Open accessAbstract
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern: (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods; and (4) baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Existing methodologies predominantly rely on heuristic techniques such as regularization-based approaches or memory replay mechanisms, which lack theoretical guarantees regarding their asymptotic behavior and scalability.
“Existing methodologies predominantly rely on heuristic techniques such as regularization-based approaches or memory replay mechanisms, which lack theoretical guarantees regarding their asymptotic behavior and scalability7.”
IL enables systems to learn new tasks over time while maintaining previous knowledge.
“IL, also termed continual or lifelong learning, enables systems to learn new tasks over time while maintaining previous knowledge [5, 6, 7], aiming to replicate human learning abilities [5].”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [5]
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · see citing works
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · see citing works
Overcoming 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 · see citing works
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · see citing works
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1× · see citing works
“Our hypothesis resembles curriculum learning [95], implying knowledge is better captured starting with the general easier tasks followed by harder specific tasks.”
BackgroundiCaRL: 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 · see citing works
Catastrophic 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 · see citing works
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562 · cited 1× · see citing works
“In recent years, machine learning models have been reported to exhibit or even surpass human level performance on individual tasks, such as Atari games [1] or object recognition [2].”
BackgroundAutomated Flower Classification over a Large Number of Classes
Nilsback, M.-E., & Zisserman, A. (2008) · 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing · doi:10.1109/icvgip.2008.47 · Cited by 3,442 · see citing works
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 · see citing works
Self-citationRiemannian 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 · see citing works
Catastrophic forgetting, rehearsal and pseudorehearsal
ROBINS, A. (1995) · Connection Science · doi:10.1080/09540099550039318 · Cited by 833 · see citing works
Measuring Catastrophic Forgetting in Neural Networks
Kemker, R., McClure, M., Abitino, A., Hayes, T., & Kanan, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11651 · Cited by 672 · see citing works
Incremental 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 · see citing works
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 · see citing works
Self-citationOvercoming 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 · see citing works
Re-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 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113 · see citing works
“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.”
BackgroundTowards 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 · see citing works
The multimodality cell segmentation challenge: toward universal solutions
Ma, J., Xie, R., Ayyadhury, S., Ge, C., Gupta, A., Gupta, R., Gu, S., Zhang, Y., Lee, G., Kim, J., et al. (2024) · Nature Methods · doi:10.1038/s41592-024-02233-6 · Cited by 154 · see citing works
Rethinking search: making domain experts out of dilettantes
Metzler, D., Tay, Y., Bahri, D., & Najork, M. (2021) · ACM SIGIR Forum · doi:10.1145/3476415.3476428 · Cited by 112 · see citing works
Semantic Communication: A Survey on Research Landscape, Challenges, and Future Directions
Getu, T. M., Kaddoum, G., & Bennis, M. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3520707 · Cited by 110 · see citing works
Dynamic Memory to Alleviate Catastrophic Forgetting in Continual Learning with Medical Imaging
Perkonigg, M., Hofmanninger, J., Herold, C. J., Brink, J. A., Pianykh, O., Prosch, H., & Langs, G. (2021) · Nature Communications · doi:10.1038/s41467-021-25858-z · Cited by 106 · see citing works
Replay in Deep Learning: Current Approaches and Missing Biological Elements
Hayes, T. L., Krishnan, G. P., Bazhenov, M., Siegelmann, H. T., Sejnowski, T. J., & Kanan, C. (2021) · Neural Computation · doi:10.1162/neco_a_01433 · Cited by 106 · see citing works
Deepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113 · see citing works
Alert Fatigue in Security Operations Centres: Research Challenges and Opportunities
Tariq, S., Baruwal Chhetri, M., Nepal, S., & Paris, C. (2025) · ACM Computing Surveys · doi:10.1145/3723158 · Cited by 101 · see citing works
Semantic anomaly detection with large language models
Elhafsi, A., Sinha, R., Agia, C., Schmerling, E., Nesnas, I. A. D., & Pavone, M. (2023) · Autonomous Robots · doi:10.1007/s10514-023-10132-6 · Cited by 101 · see citing works
Triguero, I., Molina, D., Poyatos, J., Del Ser, J., & Herrera, F. (2024) · Information Fusion · doi:10.1016/j.inffus.2023.102135 · Cited by 90 · see citing works
Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey
Zhang, J., Liu, L., Silvén, O., Pietikäinen, M., & Hu, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3529038 · Cited by 84 · see citing works
“AlthoughsomesurveysbrieflymentionFSCIL[32], [35],theyonlyprovideashortintroductiontotheconceptanda fewstudieswithoutofferingathoroughorsystematicanalysis.”
InfluentialCatastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
Aleixo, E. L., Colonna, J. G., Cristo, M., & Fernandes, E. (2023) · arXiv · doi:10.48550/arxiv.2312.10549 · Cited by 54
Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
Aleixo, E. L., Colonna, J. G., Cristo, M., & Fernandes, E. (2024) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2024.3966 · Cited by 54 · see citing works
A collective AI via lifelong learning and sharing at the edge
Soltoggio, A., Ben-Iwhiwhu, E., Braverman, V., Eaton, E., Epstein, B., Ge, Y., Halperin, L., How, J., Itti, L., Jacobs, M. A., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00800-2 · Cited by 51 · see citing works
Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition
Yuan, L., Ma, Y., Su, L., & Wang, Z. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00553 · Cited by 45 · see citing works
Continual Learning for Generative Retrieval over Dynamic Corpora
Chen, J., Zhang, R., Guo, J., de Rijke, M., Chen, W., Fan, Y., & Cheng, X. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3614821 · Cited by 40 · see citing works
Yao, J., & Kowal, J. (2025) · Energy and AI · doi:10.1016/j.egyai.2025.100585 · Cited by 30 · see citing works
DSI++: Updating Transformer Memory with New Documents
Mehta, S., Gupta, J., Tay, Y., Dehghani, M., Tran, V., Rao, J., Najork, M., Strubell, E., & Metzler, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.510 · Cited by 21 · see citing works
Continual learning of longitudinal health records
Armstrong, J., & Clifton, D. A. (2022) · 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) · doi:10.1109/bhi56158.2022.9926878 · Cited by 21 · see citing works
Lifelong Learning of Large Language Model Based Agents: A Roadmap
Zheng, J., Shi, C., Cai, X., Li, Q., Zhang, D., Li, C., Yu, D., & Ma, Q. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3650546 · Cited by 7 · see citing works
“L IFELONG learning [1], [2], also known as continual or incremental learning [3], [4], has become a key focus in the development of intelligent systems.”
Evaluating the Long-Term Memory of Large Language Models
Jia, Z., Liu, Q., Li, H., Chen, Y., & Liu, J. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.1014 · Cited by 5 · see citing works
“Inspired by re-play strategies in continual learning (Robins, 1995; Rolnick et al., 2019; De Lange et al., 2021) as well as by the replay phenomena observed in humans (Smolen et al., 2016) and in neural network models (Amiri et al., 2017), we explore whether simple continual learning strategies…”
Ye, J., Mao, Y., Song, J., Wang, X., Jin, C., & Song, M. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20219 · Cited by 1 · see citing works
Zhou, S., & Li, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-31685-9
“Existing methodologies predominantly rely on heuristic techniques such as regularization-based approaches or memory replay mechanisms, which lack theoretical guarantees regarding their asymptotic behavior and scalability 7 .”
End-to-End Test-Time Training for Long Context
Tandon, A., Dalal, K., Li, X., Koceja, D., Rød, M., Buchanan, S., Wang, X., Leskovec, J., Koyejo, S., Hashimoto, T., et al. (2025) · arXiv
“The high-level goal of continual learning is to enable AI systems to keep changing with the world, similar to how humans improve throughout their lives [36, 22].”
- Authors
- Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T.
- Affiliations
- KU Leuven (BE)
- Universitat Autònoma de Barcelona (ES)
- Huawei Technologies (Canada) (CA)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2021
- Volume
- 44
- Issue
- 7
- Pages
- 1-1
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3030364939
- Cited by
- 1,647
- References
- 18
- Citations by year
- 2026: 127 · 2025: 318 · 2024: 417 · 2023: 400 · 2022: 230 · 2021: 127 · 2020: 24 · 2019: 3 · 2012: 1
- FWCI
- 103.72
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Lirias (KU Leuven) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Departament dInnovaci Universitats i Empresa Generalitat de Catalunya (2019-FI_B2-00189)
- Huawei Technologies
- Fonds Wetenschappelijk Onderzoek
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Data Stream Mining Techniques
- Keywords
- continual learning, catastrophic forgetting, stability-plasticity trade-off, artificial neural networks, model capacity, weight decay, dropout regularization, task order effects, Tiny ImageNet, iNaturalist
- MeSH terms
- Algorithms, Learning, Neural Networks, Computer
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
