mlsanityData to 14 Oct 2026

Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learning

arXiv 2506.19558 ↗First posted 24 Jun 2025cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Few-Shot Class Incremental Learning (FSCIL) is crucial for adapting to the complex open-world environments. Contemporary prospective learning-based space construction methods struggle to balance old and new knowledge, as prototype bias and rigid structures limit the expressive capacity of the embedding space. Different from these strategies, we rethink the optimization dilemma from the perspective of feature-structure dual consistency, and propose a Consistency-driven Calibration and Matching (ConCM) framework that systematically mitigates the knowledge conflict inherent in FSCIL. Specifically, inspired by hippocampal associative memory, we design a memory-aware prototype calibration that extracts generalized semantic attributes from base classes and reintegrates them into novel classes to enhance the conceptual center consistency of features. Further, to consolidate memory associations, we propose dynamic structure matching, which adaptively aligns the calibrated features to a session-specific optimal manifold space, ensuring cross-session structure consistency. This process requires no class-number priors and is theoretically guaranteed to achieve geometric optimality and maximum matching. On large-scale FSCIL benchmarks including mini-ImageNet, CIFAR100 and CUB200, ConCM achieves state-of-the-art performance, with harmonic accuracy gains of up to 3.41% in incremental sessions. Code is available at: https://github.com/wire-wqz/ConCM

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 51 of its 74 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

51 of 74 references.

References · 51

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Learning without Forgettingcited by 2,496
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  10. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  12. 2018On First-Order Meta-Learning Algorithmscited by 1,018
38 more
  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2019Large Scale Incremental Learningcited by 732
  3. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  4. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  5. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  6. 2020Few-Shot Class-Incremental Learningcited by 251
  7. 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 198
  8. 2019Meta-Learning Representations for Continual Learningcited by 189
  9. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  10. 2023RanPAC: Random Projections and Pre-trained Models for Continual Learningcited by 164
  11. 2021Training Networks in Null Space of Feature Covariance for Continual Learningcited by 143
  12. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  13. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 116
  14. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 115
  15. 2021GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learningcited by 95
  16. 2022Constrained Few-shot Class-incremental Learningcited by 94
  17. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  18. 2020Learning to Continually Learncited by 84
  19. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 84
  20. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 56
  21. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  22. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 46
  23. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  24. 2022CoSCL: Cooperation of Small Continual Learners is Stronger than a Big Onecited by 43
  25. 2019Transductive Zero-Shot Learning with Visual Structure Constraintcited by 36
  26. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  27. 2022Continual Learning with Recursive Gradient Optimizationcited by 32
  28. 2024OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learningcited by 26
  29. 2022Few-Shot Continual Active Learning by a Robotcited by 25
  30. 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
  31. 2024CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learningcited by 11
  32. 2024Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformerscited by 9
  33. 2021Prototype Completion for Few-Shot Learningcited by 7
  34. 2024Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learningcited by 7
  35. 2025Adaptive Decision Boundary for Few-Shot Class-Incremental Learningcited by 6
  36. 2025Language-Inspired Relation Transfer for Few-shot Class-Incremental Learningcited by 5
  37. 2025Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learningcited by 4
  38. 2024Covariance-based Space Regularization for Few-shot Class Incremental Learningcited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Open Horizons: Evaluating Deep Models in the Wildcited by 0