Learning with Noisy Labels

Ask about this topic

Overview

Learning with noisy labels asks how models can learn useful decision rules when training targets disagree with the underlying truth, as often happens with crowd annotations, medical labels, and automatically generated supervision. Common approaches include robust losses and noise-transition models, sample selection and reweighting, co-teaching, label correction, and self-supervised or representation-based methods that identify suspicious examples without trusting their labels. Methods are tested on controlled synthetic corruption and real-world benchmarks such as CIFAR and Clothing1M, as well as in medical imaging, graphs, and other domains where noise may depend on the example or annotator. A central challenge is that noise structure and data difficulty matter: small-loss filtering can discard hard but correct examples, and success on closed-set synthetic benchmarks may not transfer to open-set noise or deployment settings without clean labels for evaluation.

Latest papers

CardsList

151 papers10 papers in the last four weeks, down 29% on the four weeks before. 0.1% of all new papers.

  1. What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification

    Mar 25, 2026Massa Baali, Sarthak Bisht, Rita Singh +1Speaker VerificationCurriculum Learning

    Carnegie Mellon University, Pittsburgh, USA

  2. What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

    Mar 20, 2026Dong Yan, Jian Liang, Yanbo Wang +3RL for Language Model ReasoningTest-Time RL

    School of Artificial Intelligence, University of Chinese Academy of Sciences · NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences · Nanjing University

  3. FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients

    Mar 20, 2026Tian Wen, Zhiqin Yang, Yonggang Zhang +4Federated LearningLearning with Noisy Labels

    Institute of Computing Technology, Chinese Academy of Sciences · TMLR Group, Hong Kong Baptist University · The Hong Kong University of Science and Technology +1

  4. rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks

    Mar 18, 2026Suryasis Jana, Abhik GhoshNeural Network RobustnessRobust Classification

    Indian Statistical Institute, Kolkata, India

  5. Variational Rectification Inference for Learning with Noisy Labels

    Mar 18, 2026Haoliang Sun, Qi Wei, Lei Feng +4Learning with Noisy LabelsVariational Inference

    School of Software, Shandong University, Jinan, China. · School of Computer Science and Engineering, Nanyang Technological University, Singapore. · School of Computing, National University of Singapore, Singapore. +1

  6. An assessment of data-centric methods for label noise identification in remote sensing data sets

    Mar 17, 2026Felix Kröber, Genc Hoxha, Ribana RoscherNoisy-Label LearningLearning with Noisy Labels

    Institute of Bio- and Geosciences, Forschungszentrum Jülich, Leo-Brandt-Straße, 52425 Jülich, Germany · Institute of Geodesy and Geoinformation, University of Bonn, Germany

  7. Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation

    Mar 15, 2026Wen Yan, Yipei Wang, Shiqi Huang +5Medical Image SegmentationLearning with Noisy Labels

    UCL Hawkes Institute; Department of Medical Physics and Biomedical Engineering, University College London, Gower St, London WC1E 6BT, U.K. · Centre for Medical Imaging, Division of Medicine, University College London, Gower St, London WC1E 6BT, U.K. · Division of Surgery and Interventional Science, University College London, 10 Pond St, London NW3 2PS, U.K. +2

  8. Label Noise Cleaning for Supervised Classification via Bernoulli Random Sampling

    Mar 15, 2026Yuxin Liu, Xiong Jin, Yang HanLearning with Noisy LabelsNoisy-Label Learning

    Department of Mathematics, The University of Manchester, UK · Department of Mathematics, The University of Manchester, Oxford Road, Manchester, M13 9PL, UK

  9. Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels

    Mar 14, 2026Zhanhui Lin, Yanlin Liu, Sanping ZhouNoisy-Label LearningLearning with Noisy Labels

  10. Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis

    Mar 13, 2026Chen Feng, Zhuo Zhi, Zhao Huang +5Learning with Noisy LabelsStatistical Learning Theory

    Queen’s University Belfast · University College London · University of Aberdeen +3

  11. Real-World Point Tracking with Verifier-Guided Pseudo-Labeling

    Mar 12, 2026Görkay Aydemir, Fatma Güney, Weidi XiePoint TrackingPseudo-Labeling

    Department of Computer Engineering, Koc¸ University · KUIS AI Center · School of Artificial Intelligence, Shanghai Jiao Tong University

  12. On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD

    Mar 11, 2026Tongcheng Zhang, Zhanpeng Zhou, Mingze Wang +4Two-Layer Neural NetworksNeural Network Training Dynamics

    Sch. of Computer Science and Zhiyuan College, Shanghai Jiao Tong University · Peking University · University of Sydney +4

  13. DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning

    Mar 9, 2026Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li +6Process Reward ModelsWeak-to-Strong Generalization

    The Hong Kong University of Science and Technology, Hong Kong · Genentech, Inc., South San Francisco, CA, USA.

  14. DiffInf: Influence-Guided Diffusion for Supervision Alignment in Facial Attribute Learning

    Mar 6, 2026Basudha Pal, Zhaoyang Wang, Rama ChellappaLearning with Noisy LabelsImage Classification

    Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA · Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA · Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA

  15. Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise

    Mar 6, 2026Wenxin Li, Kunyu Peng, Di Wen +63D Occupancy PredictionLearning with Noisy Labels

    School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China · Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany · INSAIT, Sofia University “St. Kliment Ohridski”, Bulgaria +1

  16. Spectral Overfitting in Noisy Linear Probing of Pretrained Representations

    Mar 2, 2026Zice Wang, Zhenyu ZhangRepresentation LearningLinear Probing

    School of Future Technology, Northeastern University, Shenyang, China.

  17. Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Binary Building Segmentation

    Feb 28, 2026Keiller Nogueira, Codrut-Andrei Diaconu, Dávid Kerekes +9Learning with Noisy LabelsNoisy-Label Learning

    School of Computer Science and Informatics, University of Liverpool, Liverpool, L69 7ZX, UK · German Aerospace Center (DLR), Remote Sensing Technology Institute, Wessling, 82234, Germany · Division of Geoinformatics, KTH Royal Institute of Technology, Stockholm, 114 28, Sweden +4

  18. Human Supervision as an Information Bottleneck: A Unified Theory of Error Floors in Human-Guided Learning

    Feb 26, 2026Alejandro Rodriguez DominguezInformation BottleneckLearning with Noisy Labels

    Miralta Finance Bank S.A., Spain · Department of Computer Science, University of Reading, UK

  19. From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification

    Feb 26, 2026Xin Yuan, Zhiyong Zhang, Xin Xu +2Person Re-IdentificationLearning with Noisy Labels

    School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, Hubei 430065, China · Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology, Wuhan 430065, China · School of Computer Science, Wuhan University, Wuhan, Hubei 430072, China +1

  20. Testable Learning of General Halfspaces under Massart Noise

    Feb 25, 2026Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane +1Halfspace LearningLearning with Noisy Labels

    UW Madison · UC San Diego

  21. Is Multi-Distribution Learning as Easy as PAC Learning: Sharp Rates with Bounded Label Noise

    Feb 24, 2026Rafael Hanashiro, Abhishek Shetty, Patrick JailletStatistical Learning TheoryLearning with Noisy Labels

    MIT

  22. Unlearning Noise in PINNs: A Selective Pruning Framework for PDE Inverse Problems

    Feb 23, 2026Yongsheng Chen, Yong Chen, Wei Guo +1Physics-Informed MLPDE Inverse Problems

    School of Mathematical Sciences, Zhejiang University, Hangzhou 310027, China. · Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA 19104, USA. · Department of Mathematics and Statistics, Texas Tech University, Lubbock, TX 70409, USA.

  23. Learning under noisy supervision is governed by a feedback-truth gap

    Feb 18, 2026Elan Schonfeld, Elias WisniaLearning with Noisy LabelsNeural Network Training Dynamics

    Department of Biology, Columbia University, New York, NY, USA · Department of Chemistry, Columbia University, New York, NY, USA

  24. Reliable Mislabel Detection for Video Capsule Endoscopy Data

    Feb 6, 2026Julia Werner, Julius Oexle, Oliver Bause +5EndoscopyMedical Imaging

    Embedded Systems University of Tübingen Tübingen, Germany · Department of Medicine I University Hospital Dresden TU Dresden, Germany

  25. Active Learning with Imperfect Labels: Optimal Labeler Assignment and Sample Selection

    Dec 14, 2025Pouya Ahadi, Blair Winograd, Camille Zaug +3Human-in-the-Loop AnnotationActive Learning

    School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332, USA · Ford Motor Company

  26. Pre-train to Gain: Robust Learning Without Clean Labels

    Nov 25, 2025David Szczecina, Nicholas Pellegrino, Paul FieguthSelf-Supervised Pre-TrainingLearning with Noisy Labels

    Systems Design Engineering University of Waterloo Waterloo, Ontario, Canada

  27. Efficient Conformal Prediction for Regression Models under Label Noise

    Sep 18, 2025Yahav Cohen, Jacob Goldberger, Tom TirerConformal PredictionLearning with Noisy Labels

    Faculty of Engineering Bar-Ilan University Ramat Gan, Israel

  28. Good Enough? An Investigation on the Impact of Label Quality in Large-Scale Medical Datasets

    May 27, 2025Alexander Jaus, Zdravko Marinov, Constantin Seibold +4Image SegmentationMedical Imaging Foundation Models

    Karlsruhe Institute of Technology, Germany · HIDSS4Health - Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany · Diagnostic and Interventional Radiology, Heidelberg University Hospital +1

  29. Hierarchical Bayesian Crowdsourcing with Item Difficulty

    May 29, 2024Seong Woo Han, Ozan Adıgüzel, Bob CarpenterInter-Rater ReliabilityLatent Variable Models

    University of Pennsylvania · Columbia University · Center for Computational Mathematics, Flatiron Institute

  30. The Re-Label Method For Data-Centric Machine Learning

    Feb 9, 2023Tong GuoLearning with Noisy LabelsHuman-in-the-Loop Annotation