CoChat
Sign Up
Cited by 110Domain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval Techniques

Few-Shot Class-Incremental Learning from an Open-Set Perspective

Open access
Peng, Can, Zhao, Kun, Wang, Tianren, Li, Meng, Lovell, Brian C.·2022·Lecture Notes in Computer Science
DOI 10.1007/978-3-031-19806-9_22
Open this paper in CoChat — free accountOpen PDF

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-031-19806-9_22

Cites

5 of 5 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

  • AA or PD values cannot reflect performance details during the continuous learning process.

    “Most studies use AA or PD values to measure model performance, but they can not reflect the performance details during the continuous learning process [47].”

    From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [47]

    Section 4.4 says class-wise average accuracy can hide poor performance on newly learned classes, and the Supplementary Material (p. 17) defines PD as the difference between the base and final sessions. These points support the need for more detailed evaluation, but the claim is too broad: the paper reports average accuracy for each incremental session, so AA does show some performance details during learning. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Some studies employ metric loss for training the embedding network, enabling it to learn more discriminative features and better adapt to incremental classes.

    “For instance, some studies [47] employ metric loss for the training of the embedding network, enabling it to learn more discriminative features and better adapt to incremental classes.”

    From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [47]

  • Current metrics assess the model's learning ability to some extent but don't completely capture the detailed performance of FSCIL throughout the continuous learning process.

    “Regarding model evaluation, while current metrics assess the model's learning ability to some extent, they don't completely capture the detailed performance of FSCIL throughout the continuous learning process [47].”

    From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [47]

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

Flagged first, then by citations

Research works printed but not linked: 20

  1. [1]Castro, F.M., Maŕın-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 233–248 (2018)
  2. [2]Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for con- trastive learning of visual representations. In: International conference on machine learning. pp. 1597–1607. PMLR (2020)
  3. [3]Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 15750–15758 (2021)
  4. [4]Cheraghian, A., Rahman, S., Fang, P., Roy, S.K., Petersson, L., Harandi, M.: Semantic-aware knowledge distillation for few-shot class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition. pp. 2534–2543 (2021)
  5. [5]Cheraghian, A., Rahman, S., Ramasinghe, S., Fang, P., Simon, C., Petersson, L., Harandi, M.: Synthesized feature based few-shot class-incremental learning on a mixture of subspaces. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 8661–8670 (2021)
  6. AAAI Conference on Artificial Intelligence. vol. 35, pp. 1255–1263 (2021)
  7. [8]Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. In: Pro- ceedings of International Conference on Learning Representations (2014)
  8. [10]Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. NIPS Deep Learning and Representation Learning Workshop (2015)
  9. [11]Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incre- mentally via rebalancing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 831–839 (2019)
  10. [12]Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., Kalantidis, Y.: Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019) · arXiv
  11. [14]Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: Sphereface: Deep hypersphere embedding for face recognition. In: Proceedings of the IEEE conference on com- puter vision and pattern recognition. pp. 212–220 (2017)
  12. [15]Mai, Z., Li, R., Kim, H., Sanner, S.: Supervised contrastive replay: Revisiting the nearest class mean classifier in online class-incremental continual learning. In: Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion. pp. 3589–3599 (2021)
  13. [18]Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recog- nition challenge. International journal of computer vision 115(3), 211–252 (2015)
  14. [19]Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., Gong, Y.: Few-shot class- incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 12183–12192 (2020)
  15. [22]Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S., Weijer, J.v.d.: Semantic drift compensation for class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6982–6991 (2020)
  16. [23]Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., Xu, Y.: Few-shot incremental learning with continually evolved classifiers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 12455–12464 (2021)
  17. [24]Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017) · arXiv
  18. [25]Zhao, H., Fu, Y., Kang, M., Tian, Q., Wu, F., Li, X.: Mgsvf: Multi-grained slow vs. fast framework for few-shot class-incremental learning. arXiv preprint arXiv:2006.15524 (2020) · arXiv
  19. [26]Zhu, F., Cheng, Z., Zhang, X.y., Liu, C.l.: Class-incremental learning via dual augmentation. Advances in Neural Information Processing Systems 34 (2021)
  20. [27]Zhu, K., Cao, Y., Zhai, W., Cheng, J., Zha, Z.J.: Self-promoted prototype refine- ment for few-shot class-incremental learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6801–6810 (2021)

Cited by

Sorted by citations

Authors
Peng, C., Zhao, K., Wang, T., Li, M., & Lovell, B. C.
Affiliations
  • The University of Queensland (AU)
  • Sullivan Nicolaides Pathology (AU)
Corresponding author
Peng, Can
ORCID
Venue
Lecture Notes in Computer Science
Publisher
Springer Nature Switzerland
Published
2022
Pages
382-397
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-031-19806-9_22
OpenAlex
W4312572119
Cited by
110
References
5
Citations by year
2026: 12 · 2025: 46 · 2024: 40 · 2023: 12
FWCI
13.55
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
Australian Government
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 class-incremental learning, open-set learning, one-shot learning, feature clustering, data augmentation, data balancing, continual learning, ALICE

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