S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning
Open accessThe 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?
Kalla and Biswas [86] proposed S3C, a method for addressing FSCIL based on the stochastic classifier [88] and self-supervision.
“Kalla and Biswas [86] proposed S3C, a method for addressing FSCIL based on the stochastic classifier [88] and self-supervision.”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [86]
The stochastic classifier weights helped mitigate the impact of limited new samples and the unavailability of old samples.
“The stochastic classifier weights helped mitigate the impact of limited new samples and the unavailability of old samples.”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [86]
The self-supervision component enabled the learning of features from base classes that generalize well to future unseen classes, effectively reducing catastrophic forgetting.
“The self-supervision component enabled the learning of features from base classes that generalize well to future unseen classes, effectively reducing catastrophic forgetting.”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [86]
Kalla and Biswas proposed the FSCIL-lb setting, which requires fewer base training samples.
“Kalla and Biswas [86] suggested the FSCIL-lb setting with fewer required base training samples”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [86]
Kalla and Biswas proposed the FSCIL-im setting, in which incremental sessions appear with an imbalanced data distribution.
“Kalla and Biswas [86] proposed the FSCIL-im setting, where the incremental sessions appear with an imbalanced data distribution”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [86]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 33 · Cited by 45
Research works printed but not linked: 42
- Akyürek, A.F., Akyürek, E., Wijaya, D., Andreas, J.: Subspace regularizers for few-shot class incremental learning. ICLR (2022)
- Belouadah, E., Popescu, A.: Scail: Classifier weights scaling for class incremental learning. In: WACV. pp. 1266-1275 (2020)
- Bhat, S.D., Banerjee, B., Chaudhuri, S.: Semgif: A semantics guided incremental few-shot learning framework with generative replay. In: BMVC (2021)
- Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural network. In: ICML. pp. 1613-1622 (2015)
- Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: ECCV. pp. 132-149 (2018)
- Castro, F.M., Marín-Jiménez, M.J., Guil, N., Schmid, C., Alahari, K.: End-to-end incremental learning. In: ECCV. pp. 233-248 (2018)
- Chen, K., Lee, C.G.: Incremental few-shot learning via vector quantization in deep embedded space. In: ICLR (2020)
- Cheraghian, A., Rahman, S., Fang, P., Roy, S.K., Petersson, L., Harandi, M.: Semantic-aware knowledge distillation for few-shot class-incremental learning. In: CVPR. pp. 2534-2543 (2021)
- 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: ICCV. pp. 8661-8670 (2021)
- Dong, S., Hong, X., Tao, X., Chang, X., Wei, X., Gong, Y.: Few-shot class- incremental learning via relation knowledge distillation. In: AAAI. pp. 1255-1263 (2021)
- Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: Podnet: Pooled outputs distillation for small-tasks incremental learning. In: ECCV 2020. pp. 86-102 (2020)
- Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: ICCV. pp. 8059-8068 (2019)
- Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. NeurIPS 32 (2019)
- Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. NeurIPS Workshop (2014)
- Hou, S., Pan, X., Loy, C.C., Wang, Z., Lin, D.: Learning a unified classifier incre- mentally via rebalancing. In: CVPR. pp. 831-839 (2019)
- Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master's thesis, Department of Computer Science, University of Toronto (2009)
- Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep con- volutional neural networks. NeurIPS 25, 1097-1105 (2012)
- Lee, E., Huang, C.H., Lee, C.Y.: Few-shot and continual learning with attentive independent mechanisms. In: ICCV. pp. 9455-9464 (2021)
- Lee, H., Hwang, S.J., Shin, J.: Self-supervised label augmentation via input trans- formations. In: ICML. pp. 5714-5724. PMLR (2020)
- Li, Z., Hoiem, D.: Learning without forgetting. TPAMI 40(12), 2935-2947 (2017)
- Lu, Z., Yang, Y., Zhu, X., Liu, C., Song, Y.Z., Xiang, T.: Stochastic classifiers for unsupervised domain adaptation. In: CVPR. pp. 9111-9120 (2020)
- Mazumder, P., Singh, P., Rai, P.: Few-shot lifelong learning. In: AAAI (2021)
- Neal, R.M.: Bayesian learning for neural networks, vol. 118. Springer Science & Business Media (2012)
- Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmen- tation. In: ICCV. pp. 1520-1528 (2015)
- Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV. pp. 69-84 (2016)
- Ouyang, W., Zeng, X., Wang, X., Qiu, S., Luo, P., Tian, Y., Li, H., Yang, S., Wang, Z., Li, H., et al.: Deepid-net: Object detection with deformable part based convolutional neural networks. TPAMI 39(7), 1320-1334 (2016)
- Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word repre- sentation. In: EMNLP. pp. 1532-1543 (2014)
- Shi, G., Chen, J., Zhang, W., Zhan, L.M., Wu, X.M.: Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. NeurIPS 34, 6747-6761 (2021)
- Tan, Z., Ding, K., Guo, R., Liu, H.: Graph few-shot class-incremental learning. WSDM (2022)
- Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., Gong, Y.: Few-shot class- incremental learning. In: CVPR. pp. 12183-12192 (2020)
- Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2017)
- Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., Fu, Y.: Large scale incre- mental learning. In: CVPR. pp. 374-382 (2019)
- Xian, Y., Schiele, B., Akata, Z.: Zero-shot learning-the good, the bad and the ugly. In: CVPR. pp. 4582-4591 (2017)
- Yang, Y., Xu, Z.: Rethinking the value of labels for improving class-imbalanced learning. NeurIPS 33, 19290-19301 (2020)
- 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: CVPR. pp. 6982-6991 (2020)
- Yu, T., Li, D., Yang, Y., Hospedales, T.M., Xiang, T.: Robust person re- identification by modelling feature uncertainty. In: ICCV. pp. 552-561 (2019)
- Zhai, X., Oliver, A., Kolesnikov, A., Beyer, L.: S4l: Self-supervised semi-supervised learning. In: ICCV. pp. 1476-1485 (2019)
- Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., Xu, Y.: Few-shot incremental learning with continually evolved classifiers. In: CVPR. pp. 12455-12464 (2021)
- Zhao, B., Xiao, X., Gan, G., Zhang, B., Xia, S.T.: Maintaining discrimination and fairness in class incremental learning. In: CVPR. pp. 13208-13217 (2020)
- Zhu, F., Cheng, Z., Zhang, X.y., Liu, C.l.: Class-incremental learning via dual augmentation. NeurIPS 34 (2021)
- Zhu, F., Zhang, X.Y., Wang, C., Yin, F., Liu, C.L.: Prototype augmentation and self-supervision for incremental learning. In: CVPR. pp. 5871-5880 (2021)
- Zhu, K., Cao, Y., Zhai, W., Cheng, J., Zha, Z.J.: Self-promoted prototype refine- ment for few-shot class-incremental learning. In: CVPR. pp. 6801-6810 (2021)
- Authors
- Kalla, J., & Biswas, S.
- Affiliations
- Indian Institute of Science Bangalore (IN)
- Corresponding author
- Kalla, Jayateja
- ORCID
- Biswas, Soma
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Nature Switzerland
- Published
- 2022
- Pages
- 432-448
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W4312865701
- Cited by
- 45
- References
- 33
- Citations by year
- 2026: 1 · 2025: 20 · 2024: 15 · 2023: 9
- FWCI
- 6.08
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Lecture notes in computer science (publishedVersion)
- NOT FOUND REPOSITORY (Indian Institute of Science Bangalore) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- 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, self-supervised learning, class prototypes, overfitting, few-shot learning, continual 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
