mlsanityData to 7 Oct 2026

Jo-SRC: A Contrastive Approach for Combating Noisy Labels

arXiv 2103.13029 ↗First posted 24 Mar 2021cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance. Existing state-of-the-art methods primarily adopt a sample selection strategy, which selects small-loss samples for subsequent training. However, prior literature tends to perform sample selection within each mini-batch, neglecting the imbalance of noise ratios in different mini-batches. Moreover, valuable knowledge within high-loss samples is wasted. To this end, we propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency). Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution. Furthermore, we propose a joint loss to advance the model generalization performance by introducing consistency regularization. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 24 Mar 2021.

Builds on

30 of 55 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  7. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  8. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  9. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  10. 2017A Closer Look at Memorization in Deep Networkscited by 936
  11. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  12. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
18 more
  1. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  2. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  3. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  4. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  5. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  6. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  7. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  8. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  9. 2017Decoupling "when to update" from "how to update"cited by 230
  10. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  11. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  12. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  13. 2018Learning to Learn from Noisy Labeled Datacited by 160
  14. 2017Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samplescited by 147
  15. 2019Deep Self-Learning From Noisy Labelscited by 122
  16. 2016Exploiting Web Images for Dataset Construction: A Domain Robust Approachcited by 22
  17. 2020Salvage Reusable Samples from Noisy Data for Robust Learningcited by 19
  18. 2017Towards Automatic Construction of Diverse, High-quality Image Datasetcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 24; 2023: 20; 2024: 15; 2025: 11; 2026: 7.

80 papers.

Sort:

By area:

  1. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  2. 2022Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCocited by 52
  3. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  4. 2022Large Loss Matters in Weakly Supervised Multi-Label Classificationcited by 38
  5. 2022Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentationcited by 37
  6. 2021Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approachcited by 32
  7. 2022Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margincited by 32
  8. 2022Neighborhood Collective Estimation for Noisy Label Identification and Correctioncited by 22
  9. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  10. 2023Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learningcited by 22
  11. 2021Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentationcited by 21
  12. 2023Rethinking Weak Supervision in Helping Contrastive Learningcited by 18
38 more
  1. 2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
  2. 2024Spatial Structure Constraints for Weakly Supervised Semantic Segmentationcited by 17
  3. 2022Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labelscited by 16
  4. 2021Addressing out-of-distribution label noise in webly-labelled datacited by 14
  5. 2023ReSup: Reliable Label Noise Suppression for Facial Expression Recognitioncited by 14
  6. 2023ScarceNet: Animal Pose Estimation with Scarce Annotationscited by 13
  7. 2022FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labelscited by 12
  8. 2023Federated Learning with Extremely Noisy Clients via Negative Distillationcited by 12
  9. 2022Is your noise correction noisy? PLS: Robustness to label noise with two stage detectioncited by 11
  10. 2022L2B: Learning to Bootstrap Robust Models for Combating Label Noisecited by 10
  11. 2023Mitigating Label Noise through Data Ambiguationcited by 10
  12. 2023Co-attention Propagation Network for Zero-Shot Video Object Segmentationcited by 9
  13. 2023Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label Noisecited by 9
  14. 2024Foster Adaptivity and Balance in Learning with Noisy Labelscited by 9
  15. 2022CNLL: A Semi-supervised Approach For Continual Noisy Label Learningcited by 8
  16. 2023Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learningcited by 8
  17. 2023Regroup Median Loss for Combating Label Noisecited by 8
  18. 2024Noisy Label Processing for Classification: A Surveycited by 8
  19. 2025Seeing What Matters: Empowering CLIP with Patch Generation-to-Selectioncited by 7
  20. 2022Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasetscited by 6
  21. 2022Label Noise-Robust Learning using a Confidence-Based Sieving Strategycited by 6
  22. 2023Combating Label Noise With A General Surrogate Model For Sample Selectioncited by 6
  23. 2024Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selectioncited by 6
  24. 2022SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labelscited by 5
  25. 2022Improving group robustness under noisy labels using predictive uncertaintycited by 4
  26. 2025Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identificationcited by 4
  27. 2022Tripartite: Tackle Noisy Labels by a More Precise Partitioncited by 3
  28. 2022The Dynamic of Consensus in Deep Networks and the Identification of Noisy Labelscited by 3
  29. 2022Denoising Multi-Similarity Formulation: A Self-paced Curriculum-Driven Approach for Robust Metric Learningcited by 3
  30. 2023GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergencecited by 3
  31. 2024Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learningcited by 3
  32. 2024Relating CNN-Transformer Fusion Network for Change Detectioncited by 3
  33. 2022Combating Noisy Labels in Long-Tailed Image Classificationcited by 2
  34. 2022Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibrationcited by 2
  35. 2023United We Stand: Using Epoch-wise Agreement of Ensembles to Combat Overfitcited by 2
  36. 2023Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learningcited by 2
  37. 2023Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learningcited by 2
  38. 2025Efficient Token Compression for Vision Transformer with Spatial Information Preservedcited by 2

50 most cited of 80 All 80 (JSON)