mlsanityData to 7 Oct 2026

Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning

arXiv 2502.08181 ↗First posted 12 Feb 2025cs.LG cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Data scarcity significantly complicates the continual learning problem, i.e., how a deep neural network learns in dynamic environments with very few samples. However, the latest progress of few-shot class incremental learning (FSCIL) methods and related studies show insightful knowledge on how to tackle the problem. This paper presents a comprehensive survey on FSCIL that highlights several important aspects i.e. comprehensive and formal objectives of FSCIL approaches, the importance of prototype rectifications, the new learning paradigms based on pre-trained model and language-guided mechanism, the deeper analysis of FSCIL performance metrics and evaluation, and the practical contexts of FSCIL in various areas. Our extensive discussion presents the open challenges, potential solutions, and future directions of FSCIL.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 49 of its 71 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

49 of 71 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  4. 2021Learning to Prompt for Continual Learningcited by 938
  5. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  6. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
  7. 2020Few-Shot Class-Incremental Learningcited by 249
  8. 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 189
  9. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  10. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  11. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  12. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
37 more
  1. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  2. 2018Don't forget, there is more than forgetting: new metrics for Continual Learningcited by 113
  3. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
  4. 2019Prototype Rectification for Few-Shot Learningcited by 96
  5. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
  6. 2022Constrained Few-shot Class-incremental Learningcited by 93
  7. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  8. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
  9. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
  10. 2020MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learningcited by 61
  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
  13. 2023Introducing Language Guidance in Prompt-based Continual Learningcited by 49
  14. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  15. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  16. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
  17. 2021Graph Few-shot Class-incremental Learningcited by 40
  18. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  19. 2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learnerscited by 35
  20. 2020XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learningcited by 30
  21. 2021GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learningcited by 26
  22. 2024OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learningcited by 25
  23. 2023Open-World Continual Learning: Unifying Novelty Detection and Continual Learningcited by 22
  24. 2022Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representationcited by 21
  25. 2024Compositional Few-Shot Class-Incremental Learningcited by 18
  26. 2024Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Promptcited by 15
  27. 2024Rethinking Few-shot Class-incremental Learning: Learning from Yourselfcited by 13
  28. 2022Learnable Distribution Calibration for Few-Shot Class-Incremental Learningcited by 12
  29. 2021Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learningcited by 11
  30. 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learningcited by 11
  31. 2023Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypescited by 10
  32. 2024An Efficient Memory Module for Graph Few-Shot Class-Incremental Learningcited by 8
  33. 2023Few-shot Class-incremental Learning for Cross-domain Disease Classificationcited by 4
  34. 2023Few-Shot Continual Learning via Flat-to-Wide Approachescited by 4
  35. 2024Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractorcited by 3
  36. 2024Inductive Graph Few-shot Class Incremental Learningcited by 2
  37. 2024Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classificationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2026Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuningcited by 11
  2. 2025Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learningcited by 1
  3. 2025Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCILcited by 0