The DOI matches its Crossref record; 28 of the 30 references it cites were found in a registry or an index.
IL2M: Class Incremental Learning With Dual Memory
Open accessAbstract
This paper presents a class incremental learning (IL) method which exploits fine tuning and a dual memory to reduce the negative effect of catastrophic forgetting in image recognition. First, we simplify the current fine tuning based approaches which use a combination of classification and distillation losses to compensate for the limited availability of past data. We find that the distillation term actually hurts performance when a memory is allowed. Then, we modify the usual class IL memory component. Similar to existing works, a first memory stores exemplar images of past classes. A second memory is introduced here to store past class statistics obtained when they were initially learned. The intuition here is that classes are best modeled when all their data are available and that their initial statistics are useful across different incremental states. A prediction bias towards newly learned classes appears during inference because the dataset is imbalanced in their favor. The challenge is to make predictions of new and past classes more comparable. To do this, scores of past classes are rectified by leveraging contents from both memories. The method has negligible added cost, both in terms of memory and of inference complexity. Experiments with three large public datasets show that the proposed approach is more effective than a range of competitive state-of-the-art methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 cited source says what the claim attributes to it.
In the citing paper
“FT BAL is also tributary to the fixed memory K because past exemplars are needed for the balancing step.”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [7]
The cited source says what the claim attributes to it.
In the citing paper
“We focus on class IL algorithms which provide the most interesting results in recent works from literature [7, 8, 14, 23, 24, 28, 56, 75].”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [7]
The cited source says what the claim attributes to it.
In the citing paper
“It is heavily affected by catastrophic forgetting if a bounded memory is not available [56] but becomes an interesting baseline if a memory is available [7].”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [7]
The cited source says what the claim attributes to it.
In the citing paper
“FT NEM can only be deployed if a bounded memory is allowed to alleviate catastrophic forgetting.”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [7]
The cited source says what the claim attributes to it.
In the citing paper
“This approach is also prone to catastrophic forgetting if no memory is allowed.”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [7]
The cited source says what the claim attributes to it.
In the citing paper
“This is explained in [7, 8, 75] by the fact that the model is biased towards new classes, leading to predict past images as belonging to new classes.”
From A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks (2020) · cites this paper as [7]
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 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
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2014.131 · Cited by 4,451
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
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
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
A systematic study of the class imbalance problem in convolutional neural networks
Buda, M., Maki, A., & Mazurowski, M. A. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.011 · Cited by 3,088 · cited 2×
“We will pursue work along the following lines: (1) test a constant complexity method such as IL2M for multitask IL to replicate real-life scenarios in which more diversified visual content is encountered, (2) enhance vanilla fine tuning by leveraging recent results which improve imbalanced learning [3] and make curric…”
BackgroundMethodVGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
Do Better ImageNet Models Transfer Better?
Kornblith, S., Shlens, J., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00277 · Cited by 1,325
Rusu, 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
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
End-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
Large-Scale Image Retrieval with Attentive Deep Local Features
Noh, H., Araújo, A. D. M., Sim, J., Weyand, T., & Han, B. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.374 · Cited by 875
Piggyback: 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 673
Li, Z., & Hoiem, D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_37 · Cited by 659
Expert 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
Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost
Mensink, T., Verbeek, J. J., Perronnin, F., & Csurka, G. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.83 · Cited by 434
FearNet: Brain-Inspired Model for Incremental LearningPreprint
Kemker, R., & Kanan, C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10563 · Cited by 414
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Guo, S., Huang, W., Zhang, H., Zhuang, C., Dong, D., Scott, M. R., & Huang, D.-L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_9 · Cited by 334
Incremental Learning Through Deep Adaptation
Rosenfeld, A., & Tsotsos, J. K. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2884462 · Cited by 260
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) · doi:10.1109/allerton.2015.7447103 · Cited by 223
Growing a Brain: Fine-Tuning by Increasing Model Capacity
Wang, Y.-X., Ramanan, D., & Hebert, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.323 · Cited by 154 · cited 2×
“A stream of research [1, 17, 27, 29] assumes that deep architectures can grow to some extent so as to integrate new data.”
BackgroundBest Practices for Fine-Tuning Visual Classifiers to New Domains
Chu, B., Madhavan, V., Beijbom, O., Hoffman, J., & Darrell, T. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-49409-8_34 · Cited by 124
Exemplar-Supported Generative Reproduction for Class Incremental Learning.
(2018) · British Machine Vision Conference (BMVC) · Cited by 60
DeeSIL: Deep-Shallow Incremental Learning
Belouadah, E., & Popescu, A. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11012-3_11 · Cited by 60
Self-citationRevisiting Distillation and Incremental Classifier Learning
Javed, K., & Shafait, F. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-20876-9_1 · Cited by 53
Flagged first, then by citations
2 of the 30 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- 10.1109/CVPR.2018.00847 · DOI
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
“IL2M [140] and SNCL [79] recover statistics of feature representations (e.g., mean and covariance) on the basis of experience replay.”
BackgroundClass-Incremental Learning: Survey and Performance Evaluation on Image Classification
Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A. D., & van de Weijer, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3213473 · Cited by 740
Maintaining Discrimination and Fairness in Class Incremental Learning
Zhao, B., Xiao, X., Gan, G., Zhang, B., & Xia, S. (2020) · 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/cvpr42600.2020.01322 · Cited by 525
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 524
Online continual learning in image classification: An empirical survey
Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., & Sanner, S. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.021 · Cited by 468
Metadata
- Authors
- Belouadah, E., & Popescu, A.
- Affiliations
- Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 583-592
- OpenAlex
- W2981864462
- Cited by
- 302
- References
- 30
- Citations by year
- 2026: 20 · 2025: 44 · 2024: 60 · 2023: 57 · 2022: 47 · 2021: 52 · 2020: 21 · 2019: 1
- FWCI
- 11.57
- Type
- conference paper
- Language
- en
- Open access
- green
- hal.science
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- HAL (submittedVersion, cc-by-nc-nd)
- 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 › Machine Learning and Data Classification
- Keywords
- class-incremental learning, catastrophic forgetting, fine-tuning, knowledge distillation, exemplar memory, image recognition, prediction bias, class imbalance
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
