mlsanityData to 7 Oct 2026

Exploring Category-correlated Feature for Few-shot Image Classification

arXiv 2112.07224 ↗First posted 14 Dec 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Few-shot classification aims to adapt classifiers to novel classes with a few training samples. However, the insufficiency of training data may cause a biased estimation of feature distribution in a certain class. To alleviate this problem, we present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge. We explicitly capture such correlation by mapping features into a latent vector with dimension matching the number of base classes, treating it as the logarithm probability of the feature over base classes. Based on this latent vector, the rectified feature is directly constructed by a decoder, which we expect maintaining category-related information while removing other stochastic factors, and consequently being closer to its class centroid. Furthermore, by changing the temperature value in softmax, we can re-balance the feature rectification and reconstruction for better performance. Our method is generic, flexible and agnostic to any feature extractor and classifier, readily to be embedded into existing FSL approaches. Experiments verify that our method is capable of rectifying biased features, especially when the feature is far from the class centroid. The proposed approach consistently obtains considerable performance gains on three widely used benchmarks, evaluated with different backbones and classifiers. The code will be made public.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

33 of 44 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2016Matching Networks for One Shot Learningcited by 2,246
  11. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  12. 2019A Closer Look at Few-shot Classificationcited by 679
21 more
  1. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  2. 2013Do Deep Nets Really Need to be Deep?cited by 466
  3. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  4. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  5. 2019A Baseline for Few-Shot Image Classificationcited by 298
  6. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  7. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  8. 2019Cross Attention Network for Few-shot Classificationcited by 218
  9. 2018Low-Shot Learning from Imaginary Datacited by 181
  10. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  11. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  12. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  13. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  14. 2019Prototype Rectification for Few-Shot Learningcited by 96
  15. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  16. 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
  17. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  18. 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
  19. 2018Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networkscited by 35
  20. 2020Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learningcited by 31
  21. 2020One-Shot Image Classification by Learning to Restore Prototypescited by 14

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  2. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  3. 2023From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learningcited by 9
  4. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3