mlsanityData to 14 Oct 2026

Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling

arXiv 2204.03749 ↗First posted 7 Apr 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

In recent works, utilizing a deep network trained on meta-training set serves as a strong baseline in few-shot learning. In this paper, we move forward to refine novel-class features by finetuning a trained deep network. Finetuning is designed to focus on reducing biases in novel-class feature distributions, which we define as two aspects: class-agnostic and class-specific biases. Class-agnostic bias is defined as the distribution shifting introduced by domain difference, which we propose Distribution Calibration Module(DCM) to reduce. DCM owes good property of eliminating domain difference and fast feature adaptation during optimization. Class-specific bias is defined as the biased estimation using a few samples in novel classes, which we propose Selected Sampling(SS) to reduce. Without inferring the actual class distribution, SS is designed by running sampling using proposal distributions around support-set samples. By powering finetuning with DCM and SS, we achieve state-of-the-art results on Meta-Dataset with consistent performance boosts over ten datasets from different domains. We believe our simple yet effective method demonstrates its possibility to be applied on practical few-shot applications.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 7 Apr 2022.

Builds on

30 of 37 references.

References · 30

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  11. 2018Meta-learning with differentiable closed-form solverscited by 397
  12. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
18 more
  1. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  2. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  3. 2019A Baseline for Few-Shot Image Classificationcited by 298
  4. 2019Cross Attention Network for Few-shot Classificationcited by 219
  5. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  6. 2018Low-Shot Learning from Imaginary Datacited by 181
  7. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  8. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  9. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  10. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  11. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  12. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  13. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  14. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  15. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  16. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  17. 2020Instance Credibility Inference for Few-Shot Learningcited by 57
  18. 2020Optimized Generic Feature Learning for Few-shot Classification across Domainscited by 23

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 1.

8 papers.

  1. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  2. 2023Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddingscited by 11
  3. 2023LSFSL: Leveraging Shape Information in Few-shot Learningcited by 4
  4. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  5. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  6. 2024A Note on Bias to Completecited by 1
  7. 2024Contextual Representation Anchor Network to Alleviate Selection Bias in Few-Shot Drug Discoverycited by 0
  8. 2025XTransfer: Modality-Agnostic Few-Shot Model Transfer for Human Sensing at the Edgecited by 0