Data to 7 Oct 2026

How does Disagreement Help Generalization against Label Corruption?

arXiv 1901.04215 ↗First posted 14 Jan 2019cs.LG stat.MLcited by 390

Not on the map. Why?

Abstract (arXiv)

Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural networks using the small-loss trick. However, with the increase of epochs, two networks converge to a consensus and Co-teaching reduces to the self-training MentorNet. To tackle this issue, we propose a robust learning paradigm called Co-teaching+, which bridges the "Update by Disagreement" strategy with the original Co-teaching. First, two networks feed forward and predict all data, but keep prediction disagreement data only. Then, among such disagreement data, each network selects its small-loss data, but back propagates the small-loss data from its peer network and updates its own parameters. Empirical results on benchmark datasets demonstrate that Co-teaching+ is much superior to many state-of-the-art methods in the robustness of trained models.

Key facts. Cited by 390 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 96; 2022: 93; 2023: 69; 2024: 63; 2025: 45; 2026: 24.

390 papers.

Sort:

By area:

2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
2021Deep Learning with Label Differential Privacycited by 113
2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
2021Augmentation Strategies for Learning with Noisy Labelscited by 86
2021FINE Samples for Learning with Noisy Labelscited by 82
2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70

38 more

2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
2021Detecting Corrupted Labels Without Training a Model to Predictcited by 57
2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 50
2022Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learningcited by 49
2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
2021From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimationcited by 48
2021Self-Damaging Contrastive Learningcited by 48
2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
2021Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptationcited by 47
2022Robust Contrastive Learning against Noisy Viewscited by 45
2021Active label cleaning for improved dataset quality under resource constraintscited by 44
2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
2021Your Classifier can Secretly Suffice Multi-Source Domain Adaptationcited by 42
2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
2024Quantifying the Gain in Weak-to-Strong Generalizationcited by 40
2021Learning Frequency Domain Approximation for Binary Neural Networkscited by 38
2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
2021Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directionscited by 35
2021Joint Negative and Positive Learning for Noisy Labelscited by 34
2021Learning from Noisy Labels for Entity-Centric Information Extractioncited by 34
2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
2022Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundariescited by 31
2022PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddingscited by 29
2022Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsingcited by 29
2022To Aggregate or Not? Learning with Separate Noisy Labelscited by 29
2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 28

50 most cited of 390 All 390 (JSON)