On Learning the Geodesic Path for Incremental Learning
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Neural networks notoriously suffer from the problem of catastrophic forgetting, the phenomenon of forgetting the past knowledge when acquiring new knowledge. Overcoming catastrophic forgetting is of significant importance to emulate the process of "incremental learning", where the model is capable of learning from sequential experience in an efficient and robust way. State-of-the-art techniques for incremental learning make use of knowledge distillation towards preventing catastrophic forgetting. Therein, one updates the network while ensuring that the network’s responses to previously seen concepts remain stable throughout updates. This in practice is done by minimizing the dissimilarity between current and previous responses of the network one way or another. Our work contributes a novel method to the arsenal of distillation techniques. In contrast to the previous state of the art, we propose to firstly construct low-dimensional manifolds for previous and current responses and minimize the dissimilarity between the responses along the geodesic connecting the manifolds. This induces a more formidable knowledge distillation with smooth properties which preserves the past knowledge more efficiently as observed by our comprehensive empirical study.1
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
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
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×
“[20] and Rebuffi [34], the gradual nature of learning plus the presence of constraints and limitations in IL can degrade the performance of the model drastically, which is formally known as “Catastrophic forgetting” [7,28,29].”
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 10×
“[22] and Rebuffi [38], the gradual nature of learning plus the presence of constraints and limitations in IL can degrade the performance of the model drastically, which is formally known as “Catastrophic forgetting” [9,30,31].”
InfluentialCatastrophic 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
Rasch, B., & Born, J. (2013) · Physiological Reviews · doi:10.1152/physrev.00032.2012 · Cited by 2,783 · cited 1×
“Finding the balance among tasks, also known as the stability-plasticity dilemma in [33], is crucial to achieve the IL ultimate goal.”
BackgroundCatastrophic forgetting in connectionist networks
French, R. (1999) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01294-2 · Cited by 2,311
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×
“A memory replay can also be achieved with a generative mechanism as proposed in [19, 35, 41], but this approach needs additional networks which are not easy to train and optimize.”
Large 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
PackNet: 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
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 10×
“[19] suggest to replay the exemplars in the memory on both old and current models and prevent the forgetting phenomenon with knowledge distillation.”
InfluentialEnd-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
Dynamic Few-Shot Visual Learning Without Forgetting
Gidaris, S., & Komodakis, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00459 · Cited by 1,128
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 · cited 1×
“Riemannian walk [4] provides a generalization framework, so-called EWC++, as an extension of EWC and an evaluation method for forgetting and intransigence.”
Universal intelligence: a definition of machine intelligence
Legg, S., & Hutter, M. (2007) · Minds and Machines · doi:10.1007/s11023-007-9079-x · Cited by 803
Cascade Models of Synaptically Stored Memories
Fusi, S., Drew, P. J., & Abbott, L. F. (2005) · Neuron · doi:10.1016/j.neuron.2005.02.001 · Cited by 569 · cited 1×
“Inspired by the synaptic consolidation from neurobiological models [8], Kirkpatrick et al.”
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
Raghu, M., Gilmer, J., Yosinski, J., & Sohl-Dickstein, J. (2017) · arXiv · doi:10.48550/arxiv.1706.05806 · Cited by 335
Mnemonics 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
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 2×
“Belouadah and Popescu [1] argue that knowledge distillation hurts the IL performance when there are at least a few examples.”
Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost
Mensink, T., Verbeek, J., Perronnin, F., & Csurka, G. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33709-3_35 · Cited by 281 · cited 1×
“Both of these methods are widely known for tasks with visual data ( e.g ., see [5, 13, 19, 32, 38]).”
Semantic-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
Self-citation
Cited by
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
“GeoDL [150] performs KD along a path that connects the low-dimensional projections of the old and new feature spaces for a smooth transition between them.”
BackgroundMethodClass-Incremental Learning: A Survey
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3429383 · Cited by 376
“There are several ways to expand representation ability, and we divide them into three sub-groups, i.e. , neuron expansion , backbone expansion , and prompt expansion .”
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
Self-citationCatastrophic 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
“Distance-based approaches benefit from using cosine distance classifiers, which have shown greater resilience to CF compared to softmax classifiers [Simon et al ., 2021; Davari et al ., 2022].”
MethodCatastrophic 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
- Simon, C., Koniusz, P., & Harandi, M.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 1591-1600
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3155950560
- Cited by
- 121
- References
- 24
- FWCI
- 10.49
- 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.