mlsanityData to 13 Oct 2026

Learning with Neighbor Consistency for Noisy Labels

arXiv 2202.02200 ↗First posted 4 Feb 2022cs.CV cs.LGcited by 55

Not on the map. Why?

Abstract (arXiv)

Recent advances in deep learning have relied on large, labelled datasets to train high-capacity models. However, collecting large datasets in a time- and cost-efficient manner often results in label noise. We present a method for learning from noisy labels that leverages similarities between training examples in feature space, encouraging the prediction of each example to be similar to its nearest neighbours. Compared to training algorithms that use multiple models or distinct stages, our approach takes the form of a simple, additional regularization term. It can be interpreted as an inductive version of the classical, transductive label propagation algorithm. We thoroughly evaluate our method on datasets evaluating both synthetic (CIFAR-10, CIFAR-100) and realistic (mini-WebVision, WebVision, Clothing1M, mini-ImageNet-Red) noise, and achieve competitive or state-of-the-art accuracies across all of them.

Key facts. Cited by 55 papers in the map (data through 13 Oct 2026). Builds on 42 of its 51 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

42 of 51 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,457
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,170
  5. 2016Matching Networks for One Shot Learningcited by 2,251
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,666
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  8. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,058
  9. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,055
  10. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  11. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  12. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
30 more
  1. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 415
  2. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  3. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  4. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  5. 2019Label Propagation for Deep Semi-supervised Learningcited by 288
  6. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  7. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 249
  8. 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
  9. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 209
  10. 2020Does label smoothing mitigate label noise?cited by 204
  11. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  12. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  13. 2018Learning to Learn from Noisy Labeled Datacited by 160
  14. 2019Does Object Recognition Work for Everyone?cited by 149
  15. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  16. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  17. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  18. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
  19. 2020A Topological Filter for Learning with Label Noisecited by 76
  20. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  21. 2020MoPro: Webly Supervised Learning with Momentum Prototypescited by 66
  22. 2020Deep k-NN for Noisy Labelscited by 55
  23. 2016Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representationscited by 50
  24. 2014Training Convolutional Networks with Noisy Labelscited by 48
  25. 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
  26. 2021Correlated Input-Dependent Label Noise in Large-Scale Image Classificationcited by 37
  27. 2017Low-shot learning with large-scale diffusioncited by 33
  28. 2021Multi-label Iterated Learning for Image Classification with Label Ambiguitycited by 19
  29. 2020Webly Supervised Image Classification with Self-Contained Confidencecited by 12
  30. 2019Graph convolutional networks for learning with few clean and many noisy labelscited by 8

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 8; 2023: 20; 2024: 10; 2025: 8; 2026: 9.

55 papers.

Sort:

By area:

  1. 2022Graph Matching with Bi-level Noisy Correspondencecited by 30
  2. 2023Improving Image Recognition by Retrieving from Web-Scale Image-Text Datacited by 20
  3. 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labelscited by 20
  4. 2024Vision-Language Models are Strong Noisy Label Detectorscited by 16
  5. 2023Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinementcited by 15
  6. 2023Mitigating Label Noise through Data Ambiguationcited by 10
  7. 2022BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classificationcited by 9
  8. 2024A Generative Approach for Wikipedia-Scale Visual Entity Recognitioncited by 9
  9. 2023Regularly Truncated M-estimators for Learning with Noisy Labelscited by 8
  10. 2023Regroup Median Loss for Combating Label Noisecited by 8
  11. 2024Generalizable Person Re-identification via Balancing Alignment and Uniformitycited by 8
  12. 2024Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domainscited by 7
38 more
  1. 2024Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learningcited by 7
  2. 2022Dynamic Loss For Robust Learningcited by 6
  3. 2023Combating Label Noise With A General Surrogate Model For Sample Selectioncited by 6
  4. 2023Data Optimization in Deep Learning: A Surveycited by 6
  5. 2022Learning with Noisy Labels over Imbalanced Subpopulationscited by 5
  6. 2022SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labelscited by 5
  7. 2022A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classificationcited by 4
  8. 2023Learning with Noisy Labels through Learnable Weighting and Centroid Similaritycited by 4
  9. 2025Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinementcited by 4
  10. 2023Towards Robust Few-shot Point Cloud Semantic Segmentationcited by 3
  11. 2023CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypescited by 3
  12. 2025Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled yet Hard-to-Learn Samples in Noisy Datacited by 3
  13. 2023LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integrationcited by 2
  14. 2023URL: Combating Label Noise for Lung Nodule Malignancy Gradingcited by 2
  15. 2023Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learningcited by 2
  16. 2025Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMscited by 2
  17. 2022Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learningcited by 1
  18. 2022Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identificationcited by 1
  19. 2023Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Modelling Approachcited by 1
  20. 2023PASS: Peer-Agreement based Sample Selection for training with Noisy Labelscited by 1
  21. 2023Label Noise: Correcting the Forward-Correctioncited by 1
  22. 2023LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labelscited by 1
  23. 2025TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrievalcited by 1
  24. 2025PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learningcited by 1
  25. 2025Multi-label Classification with Panoptic Context Aggregation Networkscited by 1
  26. 2023Variational Self-Supervised Contrastive Learning Using Beta Divergencecited by 0
  27. 2023A Unified Framework for Connecting Noise Modeling to Boost Noise Detectioncited by 0
  28. 2024Jump-teaching: Combating Sample Selection Bias via Temporal Disagreementcited by 0
  29. 2024Label Noise Robustness for Domain-Agnostic Fair Corrections via Nearest Neighbors Label Spreadingcited by 0
  30. 2024Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstructioncited by 0
  31. 2024An accurate detection is not all you need to combat label noise in web-noisy datasetscited by 0
  32. 2024Distribution-Consistency-Guided Multi-modal Hashingcited by 0
  33. 2025Noise-Tolerant Hybrid Prototypical Learning with Noisy Web Datacited by 0
  34. 2025Training Robust Graph Neural Networks by Modeling Noise Dependenciescited by 0
  35. 2026Combating Noisy Labels through Fostering Self- and Neighbor-Consistencycited by 0
  36. 2026Noise-aware few-shot learning through bi-directional multi-view prompt alignmentcited by 0
  37. 2026Variational Rectification Inference for Learning with Noisy Labelscited by 0
  38. 2026Model-agnostic information transfer and fusion for classification with label noisecited by 0

50 most cited of 55 All 55 (JSON)