mlsanityData to 7 Oct 2026

Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks

arXiv 1706.00038 ↗First posted 31 May 2017cs.LG stat.MLcited by 78

Not on the map. Why?

Abstract (arXiv)

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained cheaply. The problem is formulated using an undirected graphical model that represents the relationship between noisy and clean labels, trained in a semi-supervised setting. In our formulation, the inference over latent clean labels is tractable and is regularized during training using auxiliary sources of information. The proposed model is applied to the image labeling problem and is shown to be effective in labeling unseen images as well as reducing label noise in training on CIFAR-10 and MS COCO datasets.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 24; 2023: 12; 2024: 5; 2025: 4; 2026: 2.

78 papers.

Sort:

By area:

  1. 2021Partial success in closing the gap between human and machine visioncited by 185
  2. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  3. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  4. 2022The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generationcited by 60
  5. 2022Part-based Pseudo Label Refinement for Unsupervised Person Re-identificationcited by 59
  6. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  7. 2025Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuningcited by 39
  8. 2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
  9. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  10. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  11. 2021Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identificationcited by 29
  12. 2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 28
38 more
  1. 2023BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistencycited by 27
  2. 2023Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Modelscited by 26
  3. 2021Unified Robust Training for Graph NeuralNetworks against Label Noisecited by 21
  4. 2022NICEST: Noisy Label Correction and Training for Robust Scene Graph Generationcited by 19
  5. 2023SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labelscited by 19
  6. 2021Consistency Regularization Can Improve Robustness to Label Noisecited by 18
  7. 2021Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyondcited by 16
  8. 2023AQuA: A Benchmarking Tool for Label Quality Assessmentcited by 16
  9. 2021Generalized Data Weighting via Class-level Gradient Manipulationcited by 15
  10. 2022Scalable Penalized Regression for Noise Detection in Learning with Noisy Labelscited by 15
  11. 2022Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videoscited by 12
  12. 2022Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teachercited by 12
  13. 2022Is your noise correction noisy? PLS: Robustness to label noise with two stage detectioncited by 11
  14. 2022L2B: Learning to Bootstrap Robust Models for Combating Label Noisecited by 10
  15. 2021CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noisecited by 9
  16. 2021Noisy Annotation Refinement for Object Detectioncited by 9
  17. 2022Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Featurescited by 9
  18. 2023Latent Class-Conditional Noise Modelcited by 9
  19. 2024Foster Adaptivity and Balance in Learning with Noisy Labelscited by 9
  20. 2023Regularly Truncated M-estimators for Learning with Noisy Labelscited by 8
  21. 2024Tackling Noisy Labels with Network Parameter Additive Decompositioncited by 8
  22. 2021Learning from Noisy Labels via Dynamic Loss Thresholdingcited by 6
  23. 2021Self-paced Resistance Learning against Overfitting on Noisy Labelscited by 6
  24. 2022Narrowing the Gap: Improved Detector Training with Noisy Location Annotationscited by 6
  25. 2021Confidence Adaptive Regularization for Deep Learning with Noisy Labelscited by 5
  26. 2022Revisiting Vicinal Risk Minimization for Partially Supervised Multi-Label Classification Under Data Scarcitycited by 5
  27. 2022ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy Statecited by 5
  28. 2023Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspectscited by 5
  29. 2021Multiplicative Reweighting for Robust Neural Network Optimizationcited by 4
  30. 2022Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identificationcited by 4
  31. 2023Rank-Aware Negative Training for Semi-Supervised Text Classificationcited by 3
  32. 2024Learning Causal Transition Matrix for Instance-dependent Label Noisecited by 3
  33. 2021Enhancing Robustness of On-line Learning Models on Highly Noisy Datacited by 2
  34. 2021Training Classifiers that are Universally Robust to All Label Noise Levelscited by 2
  35. 2021NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labelscited by 2
  36. 2021Towards a Robust Differentiable Architecture Search under Label Noisecited by 2
  37. 2022Do We Need to Penalize Variance of Losses for Learning with Label Noise?cited by 2
  38. 2022Transductive CLIP with Class-Conditional Contrastive Learningcited by 2

50 most cited of 78 All 78 (JSON)