mlsanityData to 7 Oct 2026

POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples

arXiv 2206.04679 ↗First posted 8 Jun 2022cs.LG cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

In this work, we propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. Specifically, we exploit the easily available out-of-distribution samples to drive the classifier to avoid irrelevant features by maximizing the distance from prototypes to out-of-distribution samples while minimizing that of in-distribution samples (i.e., support, query data). Our approach is simple to implement, agnostic to feature extractors, lightweight without any additional cost for pre-training, and applicable to both inductive and transductive settings. Extensive experiments on various standard benchmarks demonstrate that the proposed method consistently improves the performance of pretrained networks with different architectures.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 49 of its 67 references that are in the map. First posted on arXiv 8 Jun 2022.

Builds on

49 of 67 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2016Wide Residual Networkscited by 3,057
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  11. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  12. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
37 more
  1. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  2. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  3. 2019A Closer Look at Few-shot Classificationcited by 679
  4. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  5. 2018Born Again Neural Networkscited by 539
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  9. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  10. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 403
  11. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  12. 2019A Baseline for Few-Shot Image Classificationcited by 298
  13. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  14. 2019Cross Attention Network for Few-shot Classificationcited by 218
  15. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  16. 2017Multi-task Self-Supervised Visual Learningcited by 200
  17. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  18. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  19. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  20. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  21. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  22. 2020Intriguing Properties of Contrastive Lossescited by 129
  23. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  24. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  25. 2019Prototype Rectification for Few-Shot Learningcited by 96
  26. 2020Laplacian Regularized Few-Shot Learningcited by 90
  27. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  28. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  29. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  30. 2020Empirical Bayes Transductive Meta-Learning with Synthetic Gradientscited by 48
  31. 2017Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Studycited by 46
  32. 2020Transductive Information Maximization For Few-Shot Learningcited by 44
  33. 2019Few-Shot Learning with Localization in Realistic Settingscited by 34
  34. 2020TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationcited by 30
  35. 2019Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimatorcited by 25
  36. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  37. 2018Learning Inductive Biases with Simple Neural Networkscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 6; 2024: 4; 2025: 2.

15 papers.

Sort:

  1. 2023OpenMix: Exploring Outlier Samples for Misclassification Detectioncited by 38
  2. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 22
  3. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  4. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  5. 2023Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddingscited by 11
  6. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  7. 2023DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlationcited by 4
  8. 2023PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classificationcited by 3
  9. 2023On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrievalcited by 2
  10. 2023HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settingscited by 2
  11. 2024EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logitscited by 2
  12. 2024Meta Episodic learning with Dynamic Task Sampling for CLIP-based Point Cloud Classificationcited by 0
3 more
  1. 2024Learn To Learn More Preciselycited by 0
  2. 2024Unlocking Transfer Learning for Open-World Few-Shot Recognitioncited by 0
  3. 2025Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichmentcited by 0