mlsanityData to 7 Oct 2026

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

arXiv 2107.08918 ↗First posted 19 Jul 2021cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and prototype reorganization can only be achieved under little supervision. To address this problem, we propose a novel incremental prototype learning scheme. Our scheme consists of a random episode selection strategy that adapts the feature representation to various generated incremental episodes to enhance the corresponding extensibility, and a self-promoted prototype refinement mechanism which strengthens the expression ability of the new classes by explicitly considering the dependencies among different classes. Particularly, a dynamic relation projection module is proposed to calculate the relation matrix in a shared embedding space and leverage it as the factor for bootstrapping the update of prototypes. Extensive experiments on three benchmark datasets demonstrate the above-par incremental performance, outperforming state-of-the-art methods by a margin of 13%, 17% and 11%, respectively.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 19 Jul 2021.

Builds on

22 of 37 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2019Large Scale Incremental Learningcited by 727
  9. 2019Three scenarios for continual learningcited by 610
  10. 2018End-to-End Incremental Learningcited by 596
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
10 more
  1. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 281
  2. 2020Few-Shot Class-Incremental Learningcited by 249
  3. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  4. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 220
  5. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  6. 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 110
  7. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  8. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
  9. 2020Self-Supervised Tuning for Few-Shot Segmentationcited by 17
  10. 2020Progressive One-shot Human Parsingcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 13; 2023: 32; 2024: 28; 2025: 13; 2026: 4.

95 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  3. 2022Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learningcited by 118
  4. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
  5. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  6. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
  7. 2022Representation Compensation Networks for Continual Semantic Segmentationcited by 72
  8. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
  9. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  10. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  11. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  12. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
38 more
  1. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  2. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
  3. 2021Co-Transport for Class-Incremental Learningcited by 38
  4. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  5. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  6. 2021Learning Visual Affordance Grounding from Demonstration Videoscited by 25
  7. 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
  8. 2023S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learningcited by 23
  9. 2024Generative Multi-modal Models are Good Class-Incremental Learnerscited by 22
  10. 2023Multimodal Parameter-Efficient Few-Shot Class Incremental Learningcited by 19
  11. 2022Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentationcited by 17
  12. 2021Which images to label for few-shot medical landmark detection?cited by 16
  13. 2023Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learningcited by 16
  14. 2024Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Promptcited by 15
  15. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
  16. 2023Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variantscited by 14
  17. 2023Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinementcited by 13
  18. 2024Rethinking Few-shot Class-incremental Learning: Learning from Yourselfcited by 13
  19. 2022Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometrycited by 12
  20. 2022Learnable Distribution Calibration for Few-Shot Class-Incremental Learningcited by 12
  21. 2023Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memorycited by 12
  22. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  23. 2024Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learningcited by 12
  24. 2024CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learningcited by 11
  25. 2024Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learningcited by 10
  26. 2024Adaptive Adapter Routing for Long-Tailed Class-Incremental Learningcited by 8
  27. 2025Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learningcited by 8
  28. 2024Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learningcited by 7
  29. 2024Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learningcited by 7
  30. 2023Semantic-visual Guided Transformer for Few-shot Class-incremental Learningcited by 6
  31. 2024Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modellingcited by 6
  32. 2023Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapterscited by 5
  33. 2023Continual Learning: Forget-free Winning Subnetworks for Video Representationscited by 5
  34. 2024Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learningcited by 5
  35. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  36. 2025Adaptive Decision Boundary for Few-Shot Class-Incremental Learningcited by 5
  37. 2023Forget-free Continual Learning with Soft-Winning SubNetworkscited by 4
  38. 2023Few-shot Class-incremental Learning for Cross-domain Disease Classificationcited by 4

50 most cited of 95 All 95 (JSON)