mlsanityData to 7 Oct 2026

Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid

arXiv 2210.16834 ↗First posted 30 Oct 2022cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) targets at generalization of vision models towards unseen tasks without sufficient annotations. Despite the emergence of a number of few-shot learning methods, the sample selection bias problem, i.e., the sensitivity to the limited amount of support data, has not been well understood. In this paper, we find that this problem usually occurs when the positions of support samples are in the vicinity of task centroid -- the mean of all class centroids in the task. This motivates us to propose an extremely simple feature transformation to alleviate this problem, dubbed Task Centroid Projection Removing (TCPR). TCPR is applied directly to all image features in a given task, aiming at removing the dimension of features along the direction of the task centroid. While the exact task centroid cannot be accurately obtained from limited data, we estimate it using base features that are each similar to one of the support features. Our method effectively prevents features from being too close to the task centroid. Extensive experiments over ten datasets from different domains show that TCPR can reliably improve classification accuracy across various feature extractors, training algorithms and datasets. The code has been made available at https://github.com/KikimorMay/FSL-TCBR.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 30 Oct 2022.

Builds on

41 of 63 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
29 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  3. 2019A Baseline for Few-Shot Image Classificationcited by 298
  4. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  5. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  6. 2019Cross Attention Network for Few-shot Classificationcited by 218
  7. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  8. 2018Low-Shot Learning from Imaginary Datacited by 181
  9. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  10. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  11. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  12. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  13. 2019Prototype Rectification for Few-Shot Learningcited by 96
  14. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  15. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  16. 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
  17. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  18. 2021RegNet: Self-Regulated Network for Image Classificationcited by 44
  19. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  20. 2020Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learningcited by 31
  21. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  22. 2019A Two-Stage Approach to Few-Shot Learning for Image Recognitioncited by 18
  23. 2021On sensitivity of meta-learning to support datacited by 15
  24. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  25. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  26. 2022Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Samplingcited by 8
  27. 2021Exploring Category-correlated Feature for Few-shot Image Classificationcited by 4
  28. 2021AFINet: Attentive Feature Integration Networks for Image Classificationcited by 1
  29. 2022Semantically Proportional Patchmix for Few-Shot Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 7; 2026: 1.

20 papers.

Sort:

By area:

  1. 2023A Closer Look at Few-shot Classification Againcited by 46
  2. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
  3. 2024SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agentscited by 34
  4. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  5. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  6. 2023Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddingscited by 11
  7. 2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10
  8. 2024BECLR: Batch Enhanced Contrastive Few-Shot Learningcited by 6
  9. 2025IceBerg: Debiased Self-Training for Class-Imbalanced Node Classificationcited by 4
  10. 2025Low-resource Information Extraction with the European Clinical Case Corpuscited by 3
  11. 2025Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learningcited by 2
  12. 2023P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classificationcited by 1
8 more
  1. 2023Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagationcited by 0
  2. 2023TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learningcited by 0
  3. 2024Meta Episodic learning with Dynamic Task Sampling for CLIP-based Point Cloud Classificationcited by 0
  4. 2024Contextual Representation Anchor Network to Alleviate Selection Bias in Few-Shot Drug Discoverycited by 0
  5. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  6. 2025Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Needcited by 0
  7. 2025FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learningcited by 0
  8. 2026MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decompositioncited by 0