Dynamic Few-Shot Visual Learning Without Forgetting
Abstract
The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research problem with many practical advantages on real world vision applications. In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories). To achieve that goal we propose (a) to extend an object recognition system with an attention based few-shot classification weight generator, and (b) to redesign the classifier of a ConvNet model as the cosine similarity function between feature representations and classification weight vectors. The latter, apart from unifying the recognition of both novel and base categories, it also leads to feature representations that generalize better on "unseen" categories. We extensively evaluate our approach on Mini-ImageNet where we manage to improve the prior state-of-the-art on few-shot recognition (i.e., we achieve 56.20% and 73.00% on the 1-shot and 5-shot settings respectively) while at the same time we do not sacrifice any accuracy on the base categories, which is a characteristic that most prior approaches lack. Finally, we apply our approach on the recently introduced…
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?
The practical need for learning new classes from limited samples without compromising performance on previous classes has led to the development of gFSL.
“This practical need has led to the development of a novel setting, gFSL [15], aimed at enabling learning of new classes with limited samples without compromising performance on previous classes [15, 55, 56].”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [15]
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 · see citing works
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · 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
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 · see citing works
Low-Shot Learning with Imprinted Weights
Qi, H., Brown, M., & Lowe, D. G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00610 · Cited by 539 · see citing works
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 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Label Propagation for Deep Semi-Supervised Learning
Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00521 · Cited by 686 · see citing works
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning
Chen, Y., Liu, Z., Xu, H., Darrell, T., & Wang, X. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00893 · Cited by 503 · see citing works
Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
Zhang, G., Cui, K., Hung, T.-Y., & Lu, S. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00257 · Cited by 200 · see citing works
Collect and Select: Semantic Alignment Metric Learning for Few-Shot Learning
Hao, F., He, F., Cheng, J., Wang, L., Cao, J., & Tao, D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00855 · Cited by 167 · see citing works
Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
Li, K., Min, M. R., & Fu, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00368 · Cited by 144 · 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
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
“Under this setting, most algorithms focus on not forgetting the past when learning from the present [75, 64, 57, 30].”
- Authors
- Gidaris, S., & Komodakis, N.
- Affiliations
- Paris-Est Sup (FR)
- ORCID
- Gidaris, Spyros
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 4367-4375
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2798836702
- Cited by
- 1,128
- References
- 7
- Citations by year
- 2026: 30 · 2025: 87 · 2024: 137 · 2023: 172 · 2022: 201 · 2021: 250 · 2020: 173 · 2019: 72 · 2018: 6
- FWCI
- 51.13
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- 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 › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- few-shot learning, visual recognition, novel category recognition, unseen category generalization, miniImageNet
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
