mlsanityData to 14 Oct 2026

LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment

arXiv 2103.04173 ↗First posted 6 Mar 2021cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue. The most competitive noisy-label learning algorithms rely on a 2-stage process comprising an unsupervised learning to classify training samples as clean or noisy, followed by a semi-supervised learning that minimises the empirical vicinal risk (EVR) using a labelled set formed by samples classified as clean, and an unlabelled set with samples classified as noisy. In this paper, we hypothesise that the generalisation of such 2-stage noisy-label learning methods depends on the precision of the unsupervised classifier and the size of the training set to minimise the EVR. We empirically validate these two hypotheses and propose the new 2-stage noisy-label training algorithm LongReMix. We test LongReMix on the noisy-label benchmarks CIFAR-10, CIFAR-100, WebVision, Clothing1M, and Food101-N. The results show that our LongReMix generalises better than competing approaches, particularly in high label noise problems. Furthermore, our approach achieves state-of-the-art performance in most datasets. The code is available at https://github.com/filipe-research/LongReMix.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 46 of its 63 references that are in the map. First posted on arXiv 6 Mar 2021.

Builds on

46 of 63 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  5. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  8. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  9. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  10. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  11. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  12. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
34 more
  1. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 678
  2. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  3. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  4. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  5. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  6. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  7. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  8. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  9. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  10. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  11. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  12. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  13. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
  14. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  15. 2017Decoupling "when to update" from "how to update"cited by 230
  16. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  17. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  18. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  19. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  20. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  21. 2018Learning to Learn from Noisy Labeled Datacited by 160
  22. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  23. 2019Deep Self-Learning From Noisy Labelscited by 122
  24. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  25. 2017Learning with Biased Complementary Labelscited by 93
  26. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  27. 2019Robust Inference via Generative Classifiers for Handling Noisy Labelscited by 68
  28. 2019Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classificationcited by 33
  29. 2019IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matterscited by 33
  30. 2018A Semi-Supervised Two-Stage Approach to Learning from Noisy Labelscited by 29
  31. 2020EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labelscited by 28
  32. 2019Photometric Transformer Networks and Label Adjustment for Breast Density Predictioncited by 10
  33. 2018Generalization Bounds for Vicinal Risk Minimization Principlecited by 4
  34. 2020Reliable Label Bootstrapping for Semi-Supervised Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 7; 2024: 9; 2025: 9; 2026: 6.

40 papers.

Sort:

By area:

  1. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  2. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  3. 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labelscited by 20
  4. 2022Uni4Eye: Unified 2D and 3D Self-supervised Pre-training via Masked Image Modeling Transformer for Ophthalmic Image Classificationcited by 18
  5. 2024Vision-Language Models are Strong Noisy Label Detectorscited by 16
  6. 2021ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learningcited by 13
  7. 2021SSR: An Efficient and Robust Framework for Learning with Unknown Label Noisecited by 13
  8. 2024Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Namescited by 11
  9. 2021Sample Prior Guided Robust Model Learning to Suppress Noisy Labelscited by 8
  10. 2024Noisy Label Processing for Classification: A Surveycited by 8
  11. 2024Learning to Complement and to Defer to Multiple Userscited by 7
  12. 2025Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimizationcited by 6
28 more
  1. 2023Learning to Complement with Multiple Humanscited by 5
  2. 2025SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixingcited by 5
  3. 2022Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labelscited by 4
  4. 2021CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learningcited by 3
  5. 2024ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labelscited by 3
  6. 2025Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlookcited by 3
  7. 2023LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integrationcited by 2
  8. 2023Mitigating Label Bias in Machine Learning: Fairness through Confident Learningcited by 2
  9. 2025Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalizationcited by 2
  10. 2023PASS: Peer-Agreement based Sample Selection for training with Noisy Labelscited by 1
  11. 2024Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmarkcited by 1
  12. 2025Open set label noise learning with robust sample selection and margin-guided modulecited by 1
  13. 2025Fair Bayesian Data Selection via Generalized Discrepancy Measurescited by 1
  14. 2022Class Prototype-based Cleaner for Label Noise Learningcited by 0
  15. 2023Robust Remote Sensing Scene Classification with Multi-View Voting and Entropy Rankingcited by 0
  16. 2023A Unified Framework for Connecting Noise Modeling to Boost Noise Detectioncited by 0
  17. 2024Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstructioncited by 0
  18. 2024An accurate detection is not all you need to combat label noise in web-noisy datasetscited by 0
  19. 2024Learning from Noisy Labels for Long-tailed Data via Optimal Transportcited by 0
  20. 2025Uncertainty Aware Human-machine Collaboration in Camouflaged Object Detectioncited by 0
  21. 2025Learning to Clean: Reinforcement Learning for Noisy Label Correctioncited by 0
  22. 2025Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Datacited by 0
  23. 2026ACD-U: Asymmetric co-teaching with machine unlearning for robust learning with noisy labelscited by 0
  24. 2026Risk-Aware Robust Learning: Reducing Clinical Risk under Label Noise in Medical Image Classificationcited by 0
  25. 2026HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labelscited by 0
  26. 2026Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learningcited by 0
  27. 2026Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Labelcited by 0
  28. 2026GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labelscited by 0