mlsanityData to 7 Oct 2026

Prototype Rectification for Few-Shot Learning

arXiv 1911.10713 ↗First posted 25 Nov 2019cs.CVcited by 96

Not on the map. Why?

Abstract (arXiv)

Few-shot learning requires to recognize novel classes with scarce labeled data. Prototypical network is useful in existing researches, however, training on narrow-size distribution of scarce data usually tends to get biased prototypes. In this paper, we figure out two key influencing factors of the process: the intra-class bias and the cross-class bias. We then propose a simple yet effective approach for prototype rectification in transductive setting. The approach utilizes label propagation to diminish the intra-class bias and feature shifting to diminish the cross-class bias. We also conduct theoretical analysis to derive its rationality as well as the lower bound of the performance. Effectiveness is shown on three few-shot benchmarks. Notably, our approach achieves state-of-the-art performance on both miniImageNet (70.31% on 1-shot and 81.89% on 5-shot) and tieredImageNet (78.74% on 1-shot and 86.92% on 5-shot).

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 27; 2023: 16; 2024: 13; 2025: 8; 2026: 5.

96 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  3. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  4. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  5. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
  6. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  7. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  8. 2024Boosting Vision-Language Models with Transductioncited by 36
  9. 2024Transductive Zero-Shot and Few-Shot CLIPcited by 31
  10. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  11. 2021Dual-Awareness Attention for Few-Shot Object Detectioncited by 29
  12. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
38 more
  1. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 26
  2. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  3. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  4. 2022Domain-Agnostic Prior for Transfer Semantic Segmentationcited by 18
  5. 2024Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentationcited by 16
  6. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  7. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  8. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  9. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
  10. 2022Self-Regularized Prototypical Network for Few-Shot Semantic Segmentationcited by 12
  11. 2024Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Datacited by 12
  12. 2021MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learningcited by 11
  13. 2025ProtoDepth: Unsupervised Continual Depth Completion with Prototypescited by 11
  14. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  15. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  16. 2022Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inferencecited by 9
  17. 2021Nearest Neighbour Few-Shot Learning for Cross-lingual Classificationcited by 8
  18. 2023Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentationcited by 8
  19. 2023Prototypes-oriented Transductive Few-shot Learning with Conditional Transportcited by 8
  20. 2024Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classificationcited by 8
  21. 2024Boosting Vision-Language Models for Histopathology Classification: Predict all at oncecited by 8
  22. 2021Sill-Net: Feature Augmentation with Separated Illumination Representationcited by 7
  23. 2021Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classificationcited by 7
  24. 2021Prototype Completion for Few-Shot Learningcited by 7
  25. 2021Fine-Grained Few Shot Learning with Foreground Object Transformationcited by 7
  26. 2022Personalized Keyword Spotting through Multi-task Learningcited by 7
  27. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  28. 2023Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptationcited by 7
  29. 2022Temporal Transductive Inference for Few-Shot Video Object Segmentationcited by 6
  30. 2021Diffusion Mechanism in Residual Neural Network: Theory and Applicationscited by 5
  31. 2022GDC- Generalized Distribution Calibration for Few-Shot Learningcited by 5
  32. 2021Transductive Few-Shot Learning: Clustering is All You Need?cited by 4
  33. 2021SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classificationcited by 4
  34. 2021Exploring Category-correlated Feature for Few-shot Image Classificationcited by 4
  35. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  36. 2023Decomposed Prototype Learning for Few-Shot Scene Graph Generationcited by 4
  37. 2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
  38. 2024Few-Shot Class Incremental Learning via Robust Transformer Approachcited by 4

50 most cited of 96 All 96 (JSON)