mlsanityData to 7 Oct 2026

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

arXiv 2312.05229 ↗First posted 8 Dec 2023cs.CV cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new classes and maintain the knowledge of base classes. In this Few-Shot Class-Incremental Learning (FSCIL) scenario, existing methods either introduce extra learnable components or rely on a frozen feature extractor to mitigate catastrophic forgetting and overfitting problems. However, we find a tendency for existing methods to misclassify the samples of new classes into base classes, which leads to the poor performance of new classes. In other words, the strong discriminability of base classes distracts the classification of new classes. To figure out this intriguing phenomenon, we observe that although the feature extractor is only trained on base classes, it can surprisingly represent the semantic similarity between the base and unseen new classes. Building upon these analyses, we propose a simple yet effective Training-frEE calibratioN (TEEN) strategy to enhance the discriminability of new classes by fusing the new prototypes (i.e., mean features of a class) with weighted base prototypes. In addition to standard benchmarks in FSCIL, TEEN demonstrates remarkable performance and consistent improvements over baseline methods in the few-shot learning scenario. Code is available at: https://github.com/wangkiw/TEEN

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 42 of its 59 references that are in the map. First posted on arXiv 8 Dec 2023.

Builds on

42 of 59 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2016Densely Connected Convolutional Networkscited by 6,691
  9. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  10. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  11. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  12. 2016Learning without Forgettingcited by 2,465
30 more
  1. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  2. 2016Matching Networks for One Shot Learningcited by 2,246
  3. 2018Experience Replay for Continual Learningcited by 1,074
  4. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  5. 2019Large Scale Incremental Learningcited by 727
  6. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  7. 2018End-to-End Incremental Learningcited by 596
  8. 2019Gradient based sample selection for online continual learningcited by 568
  9. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  10. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  11. 2018How to train your MAMLcited by 306
  12. 2020Few-Shot Class-Incremental Learningcited by 249
  13. 2018Selective Experience Replay for Lifelong Learningcited by 239
  14. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  15. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  16. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  17. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  18. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  19. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  20. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  21. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
  22. 2019Prototype Rectification for Few-Shot Learningcited by 96
  23. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
  24. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  25. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  26. 2023RMM: Reinforced Memory Management for Class-Incremental Learningcited by 66
  27. 2023PILOT: A Pre-Trained Model-Based Continual Learning Toolboxcited by 64
  28. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
  29. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  30. 2020Revisiting Meta-Learning as Supervised Learningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 18; 2026: 7.

44 papers.

Sort:

By area:

  1. 2024Continual Learning with Pre-Trained Models: A Surveycited by 151
  2. 2024Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learningcited by 115
  3. 2024Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Promptcited by 15
  4. 2024Rethinking Few-shot Class-incremental Learning: Learning from Yourselfcited by 13
  5. 2024Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformerscited by 9
  6. 2024Adaptive Adapter Routing for Long-Tailed Class-Incremental Learningcited by 8
  7. 2025Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learningcited by 8
  8. 2024Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learningcited by 7
  9. 2025Generalized Incremental Learning under Concept Drift across Evolving Data Streamscited by 7
  10. 2024Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learningcited by 5
  11. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  12. 2025Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learningcited by 3
32 more
  1. 2024Covariance-based Space Regularization for Few-shot Class Incremental Learningcited by 2
  2. 2025Information-Theoretic Generalization Bounds of Replay-based Continual Learningcited by 2
  3. 2025DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learningcited by 2
  4. 2026Test-Time Mixture of World Models for Embodied Agents in Dynamic Environmentscited by 2
  5. 2024Bias Mitigating Few-Shot Class-Incremental Learningcited by 1
  6. 2024Controllable Relation Disentanglement for Few-Shot Class-Incremental Learningcited by 1
  7. 2024Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classificationcited by 1
  8. 2024From Uncertainty to Clarity: Uncertainty-Guided Class-Incremental Learning for Limited Biomedical Samples via Semantic Expansioncited by 1
  9. 2024Knowledge Adaptation Network for Few-Shot Class-Incremental Learningcited by 1
  10. 2024CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learningcited by 1
  11. 2025Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learningcited by 1
  12. 2025Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learningcited by 1
  13. 2025Few-Shot Class-Incremental Model Attribution Using Learnable Representation From CLIP-ViT Featurescited by 1
  14. 2025Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learningcited by 1
  15. 2025Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learningcited by 1
  16. 2025The Bayesian Approach to Continual Learning: An Overviewcited by 1
  17. 2026G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphscited by 1
  18. 2024Continual Gesture Learning without Data via Synthetic Feature Samplingcited by 0
  19. 2024Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Imagescited by 0
  20. 2024AnchorInv: Few-Shot Class-Incremental Learning of Physiological Signals via Representation Space Guided Inversioncited by 0
  21. 2025Brain-inspired analogical mixture prototypes for few-shot class-incremental learningcited by 0
  22. 2025Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculturecited by 0
  23. 2025Class-Incremental Learning for Honey Botanical Origin Classification with Hyperspectral Images: A Study with Continual Backpropagationcited by 0
  24. 2025Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learningcited by 0
  25. 2025Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCILcited by 0
  26. 2025SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Networkcited by 0
  27. 2025Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusioncited by 0
  28. 2026Few-shot Class-Incremental Learning via Generative Co-Memory Regularizationcited by 0
  29. 2026CASP: Few-Shot Class-Incremental Learning with CLS Token Attention Steering Promptscited by 0
  30. 2026Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learningcited by 0
  31. 2026UNIT: Unleash Large Language Models Potential for Graph Continual Learningcited by 0
  32. 2026Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph-Text Modelscited by 0