Efficient Feature Transformations for Discriminative and Generative Continual Learning
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown promise by naturally adding model capacity for learning new tasks while simultaneously avoiding catastrophic forgetting. However, the growth in the number of additional parameters of many of these types of methods can be computationally expensive at larger scales, at times prohibitively so. Instead, we propose a simple task-specific feature map transformation strategy for continual learning, which we call Efficient Feature Transformations (EFTs). These EFTs provide powerful flexibility for learning new tasks, achieved with minimal parameters added to the base architecture. We further propose a feature distance maximization strategy, which significantly improves task prediction in class incremental settings, without needing expensive generative models. We demonstrate the efficacy and efficiency of our method with an extensive set of experiments in discriminative (CIFAR-100 and ImageNet-1K) and generative (LSUN, CUB-200, Cats) sequences of tasks. Even with low single-digit parameter growth rates, EFTs can outperform many other continual learning methods in a wide range of settings.
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.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
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
Li, 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 1×
“As the number of tasks grows, performance degrades quickly, especially in large-scale settings [38, 40].”
BackgroundCatastrophic 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
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
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
Continual Learning Through Synaptic Intelligence
Zenke, F., Poole, B., & Ganguli, S. (2017) · arXiv · doi:10.48550/arxiv.1703.04200 · Cited by 1,784
A 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
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
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
Gradient Episodic Memory for Continual Learning
Lopez-Paz, D., & Ranzato, M. (2017) · arXiv · doi:10.48550/arxiv.1706.08840 · Cited by 1,403
Continual 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×
“Replay methods [27, 46, 36, 42] retain knowledge by rehearsing on data saved from previous tasks.”
MethodPackNet: 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
Riemannian 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
Ratcliff, R. (1990) · Psychological Review · doi:10.1037//0033-295x.97.2.285 · Cited by 941
Experience Replay for Continual Learning
Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T. P., & Wayne, G. (2018) · arXiv · doi:10.48550/arxiv.1811.11682 · Cited by 529 · cited 1×
“Replay methods [27, 46, 36, 42] retain knowledge by rehearsing on data saved from previous tasks.”
MethodVariational 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 2×
“Regularization-based methods [18, 62, 36, 1, 41] prevent forgetting by constraining model parameters from drifting too far away from previous solutions, but they can also restrict the model’s ability to adapt to new tasks, often resulting in sub-optimal solutions.”
BackgroundMethodVariational Continual Learning
Turner, R., Bui, T., Li, Y., & Cuong, N. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.35471 · Cited by 438
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
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 · cited 2×
“Knowing which task t an inference-time input corresponds to is a common implicit assumption in continual learning, but in some settings this information is unavailable, necessitating predicting the task t alongside the class; such a setting has been referred to as class incremental learning (CIL) [15].”
BackgroundWortsman, M., Ramanujan, V., Liu, R., Kembhavi, A., Rastegari, M., Yosinski, J., & Farhadi, A. (2020) · arXiv · doi:10.48550/arxiv.2006.14769 · Cited by 144 · cited 6×
“We compare our EFTs with the recently proposed SupSup [54] and BatchE [53] on CIFAR-100/20 in the task incremental setting, showing the results in Table 9.”
MethodResultInfluential
Cited by
A Metaverse: Taxonomy, Components, Applications, and Open Challenges
Park, S.-M., & Kim, Y.-G. (2022) · IEEE Access · doi:10.1109/access.2021.3140175 · Cited by 1,824
Three types of incremental learning
van de Ven, G. M., Tuytelaars, T., & Tolias, A. S. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00568-3 · Cited by 665
Catastrophic 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
“In the context of GANs, Verma et al .”
BackgroundA 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
“A similar concept is also exploited in other studies 102,103,148–150 , where task-agnostic backbones are combined with small sets of task-specific parameters that allow for knowledge transfer with minimal changes to a model 151,152 .”
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
Metadata
- Authors
- Verma, V. K., Liang, K. J., Mehta, N., Rai, P., & Carin, L.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 13860-13870
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3135917893
- Cited by
- 62
- References
- 29
- FWCI
- 6.29
- Type
- conference paper
- Language
- en
- Open access
- green
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.