Few-Shot Class-Incremental Learning via Relation Knowledge Distillation
Open accessAbstract
In this paper, we focus on the challenging few-shot class incremental learning (FSCIL) problem, which requires to transfer knowledge from old tasks to new ones and solves catastrophic forgetting. We propose the exemplar relation distillation incremental learning framework to balance the tasks of old-knowledge preserving and new-knowledge adaptation. First, we construct an exemplar relation graph to represent the knowledge learned by the original network and update gradually for new tasks learning. Then an exemplar relation loss function for discovering the relation knowledge between different classes is introduced to learn and transfer the structural information in relation graph. A large number of experiments demonstrate that relation knowledge does exist in the exemplars and our approach outperforms other state-of-the-art class-incremental learning methods on the CIFAR100, miniImageNet, and CUB200 datasets.
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
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 relation KD framework constructed a sample relation graph to represent learned knowledge, ensuring balance by selecting an equal number of samples from each base class.
“They constructed a sample relation graph to represent learned knowledge, ensuring balance by selecting an equal number of samples from each base class.”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [92]
Dong et al. [92] proposed a relation KD framework.
“Dong et al. [92] proposed a relation KD framework.”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [92]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
This paper’s reference list could not be split into single entries.
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
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
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
Topology-Preserving Class-Incremental Learning
Tao, X., Chang, X., Hong, X., Wei, X., & Gong, Y. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58529-7_16 · Cited by 162 · see citing works
Self-citation
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
“The extremely limited training samples exacerbate the overfitting of previously-learned representations to subsequent tasks, which can be alleviated by recent work such as preserving the topology of representations (TOPIC [404]), constructing an exemplar relation graph for knowledge distillation (ERL [97]), selectivel…”
BackgroundFew-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
“In Table IV, the top five methods with the lowest PD values on mini ImageNet are: MgSvF [22] (17.33%), SFbFSCIL [79] (19.14%), SPPR [69] (19.53%), ERL++ [92] (20.94%), and DSN (21.06%).”
Influential
- Authors
- Dong, S., Hong, X., Tao, X., Chang, X., Wei, X., & Gong, Y.
- Affiliations
- Xi'an Jiaotong University (CN)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2021-05-18
- Volume
- 35
- Issue
- 2
- Pages
- 1255-1263
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W3176779063
- Cited by
- 161
- References
- 5
- Citations by year
- 2026: 13 · 2025: 42 · 2024: 46 · 2023: 38 · 2022: 20 · 2021: 2
- FWCI
- 12.24
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Funders
- National Natural Science Foundation of China (62076195, 2020M683489, 2020AAA0105600, 62006183)
- China Postdoctoral Science Foundation (2020AAA0105600, 2020M683489, 62006183)
- 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
- few-shot class-incremental learning, catastrophic forgetting, knowledge distillation, knowledge transfer, incremental learning, exemplar-based learning
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
