mlsanityData to 7 Oct 2026

Few-shot Learning with Noisy Labels

arXiv 2204.05494 ↗First posted 12 Apr 2022cs.CV stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled samples. Robustness to label noise is therefore essential for FSL methods to be practical, but this problem surprisingly remains largely unexplored. To address mislabeled samples in FSL settings, we make several technical contributions. (1) We offer simple, yet effective, feature aggregation methods, improving the prototypes used by ProtoNet, a popular FSL technique. (2) We describe a novel Transformer model for Noisy Few-Shot Learning (TraNFS). TraNFS leverages a transformer's attention mechanism to weigh mislabeled versus correct samples. (3) Finally, we extensively test these methods on noisy versions of MiniImageNet and TieredImageNet. Our results show that TraNFS is on-par with leading FSL methods on clean support sets, yet outperforms them, by far, in the presence of label noise.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 51 of its 71 references that are in the map. First posted on arXiv 12 Apr 2022.

Builds on

51 of 71 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  11. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  12. 2017A Closer Look at Memorization in Deep Networkscited by 936
38 more
  1. 2019A Closer Look at Few-shot Classificationcited by 679
  2. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
  3. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  4. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  5. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  6. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  7. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  8. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  9. 2018Meta-learning with differentiable closed-form solverscited by 395
  10. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  11. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  12. 2020Are we done with ImageNet?cited by 329
  13. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  14. 2018How to train your MAMLcited by 306
  15. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  16. 2017Meta Networkscited by 268
  17. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  18. 2017A General and Adaptive Robust Loss Functioncited by 236
  19. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  20. 2017Learning from Noisy Labels with Distillationcited by 160
  21. 2018Learning to Learn from Noisy Labeled Datacited by 160
  22. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  23. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  24. 2018Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifierscited by 126
  25. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  26. 2019Improved Few-Shot Visual Classificationcited by 114
  27. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  28. 2019Meta Label Correction for Noisy Label Learningcited by 108
  29. 2020From ImageNet to Image Classification: Contextualizing Progress on Benchmarkscited by 90
  30. 2020learn2learn: A Library for Meta-Learning Researchcited by 69
  31. 2020MixKD: Towards Efficient Distillation of Large-scale Language Modelscited by 65
  32. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  33. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  34. 2020Learning from Few Samples: A Surveycited by 23
  35. 2021Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detectioncited by 23
  36. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  37. 2020Object Detection as a Positive-Unlabeled Problemcited by 18
  38. 2020RNNP: A Robust Few-Shot Learning Approachcited by 9

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 7; 2025: 1; 2026: 1.

23 papers.

Sort:

By area:

  1. 2023EgoTracks: A Long-term Egocentric Visual Object Tracking Datasetcited by 27
  2. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  3. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  4. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  5. 2022Robust Active Distillationcited by 9
  6. 2023Regularly Truncated M-estimators for Learning with Noisy Labelscited by 8
  7. 2024DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Modelscited by 5
  8. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  9. 2023Towards Robust Few-shot Point Cloud Semantic Segmentationcited by 3
  10. 2023Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Datacited by 2
  11. 2023HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settingscited by 2
  12. 2024Data-Efficient and Robust Task Selection for Meta-Learningcited by 2
11 more
  1. 2023LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labelscited by 1
  2. 2024Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labelscited by 1
  3. 2022FedAR+: A Federated Learning Approach to Appliance Recognition with Mislabeled Data in Residential Buildingscited by 0
  4. 2023Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Workcited by 0
  5. 2023BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noisecited by 0
  6. 2023Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Modelscited by 0
  7. 2023Batch Selection and Communication for Active Learning with Edge Labelingcited by 0
  8. 2024Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classificationcited by 0
  9. 2024On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learningcited by 0
  10. 2024CRoF: CLIP-based Robust Few-shot Learning on Noisy Labelscited by 0
  11. 2026TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Modelscited by 0