Overview

Noisy-label learning studies how models can learn when training labels are wrong, uncertain, or supplied by annotators with differing reliability. Common approaches include robust loss functions, small-loss sample selection and co-teaching, modeling annotator or label-noise processes, and detecting, reweighting, or correcting suspicious labels; newer work also adapts these ideas to language models, preference data, and federated learning. The field combines theoretical analyses of learnability under specific noise assumptions with empirical tests on benchmarks and naturally noisy datasets. A central tension is that filtering or correcting labels can reduce harmful supervision but also discard difficult, informative examples, and methods that work for one noise structure or data setting may fail in another.

Latest papers

CardsList

101 papers8 papers in the last four weeks, down 20% on the four weeks before. 0.1% of all new papers.

  1. Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework

    Nov 16, 2026Zijian Zhao, Davide Di Monda, Domenico Ciuonzo +2Network Intrusion DetectionClass-Incremental Learning

  2. Dual-Granularity Learning for Regression with Continuous Noisy Labels

    Nov 7, 2026Hui Guo, Boyu Wang, Grace Y. YiNoisy-Label LearningLearning with Noisy Labels

  3. LLM-Assisted Label Noise Correction for EEG-Based Sleep Stage Classification

    Nov 5, 2026Elmira Salari, Shruti KshirsagarSleep Stage ClassificationNoisy-Label Learning

  4. Semantic Prior-Guided Incomplete Cross-Modal Retrieval with Noisy Labels

    Nov 4, 2026Jiali Chen, Ruitao Pu, Yingke Chen +1Cross-Modal RetrievalMissing-Modality Learning

  5. Robust EEG-based Emotion Recognition from Coarse Trial-level Labels under Intra-trial Affective Variability

    Nov 1, 2026Xiaocong Zeng, Buxuan Wang, Xin Yang +2EEG Emotion RecognitionAffective Computing

  6. Smooth bounding box for object detection

    Oct 31, 2026Chao Zhou, Shenghua He, Fengchuang Xing +2Object DetectionNoisy-Label Learning

  7. Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR

    Oct 23, 2026Shashi Kumar, Yanis Labrak, Sergio Burdisso +4Automatic Speech RecognitionDomain Adaptation for ASR

  8. Sam-Correction: Fully Adaptive Label Noise Reduction for Medical Image Segmentation

    Oct 23, 2026Takuro Shimaya, Masahiro SaikoMedical Image SegmentationNoisy-Label Learning

  9. CAVA: Complementary-Label-Aware Data Valuation

    Oct 19, 2026Tan-Ha Mai, Hsuan-Tien Lin, Vu NguyenData ValuationLearning with Noisy Labels

  10. A Topological Signature of Learning under Noisy Labels

    Oct 16, 2026Zhongtian Sun, Fan Mo, Prayag Tiwari +1Noisy-Label LearningNeural Representation Geometry

  11. A Label Noise Robust Algorithm for Graph Data using Neighborhood Label Distribution

    Oct 16, 2026Pintu Kumar, Nandyala HemachandraGraph Neural NetworksNoisy-Label Learning

  12. CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF

    Oct 15, 2026Licheng Pan, Haocheng Yang, Yuzhou Chen +7RL from Human FeedbackNoisy-Label Learning

  13. Wrong Votes, Right Gradients: Why Majority-Vote Rewards Track Verifiable RL

    Oct 14, 2026Dylan P. Wilson, Chengsong Huang, Jiaxin HuangRL for Language Model ReasoningNoisy-Label Learning

  14. Calibrated Disambiguation for Partial Multi-label Learning

    Oct 13, 2026Zhuoming Li, Yuheng Jia, Mi Yu +1Multi-Label ClassificationNoisy-Label Learning

  15. Toward Reliable Infant Pose Estimation: A Training-Dynamics Approach to Noisy Annotation Detection

    Oct 5, 2026Emanuele Cardinale, Sara Moccia, Alessandro Cacciatore +1Markerless Motion CaptureNoisy-Label Learning

  16. Prompt and Refinement: Asymmetric Mutual Learning for Infrared Small Target Detection with Noisy Labels

    Oct 5, 2026Yimin Fu, Songbo Wang, Lizhuo Liu +3Infrared Small Target DetectionNoisy-Label Learning

  17. PTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport Problems

    Sep 30, 2026Yubo Cao, Xi Deng, Mengqi Xia +3Neural Surrogate ModelingNoisy-Label Learning

  18. Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification

    Sep 30, 2026Xabier de Juan, Santiago Mazuelas, Yilun Zhu +1Noisy-Label LearningStatistical Learning Theory

  19. Pretrained ASR Pseudo-labeling for Noisy Police Audio

    Sep 24, 2026Kaavya Chaparala, Su Huang, Stephen L. Morgan +2Domain Adaptation for ASRAutomatic Speech Recognition

  20. TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models

    Sep 15, 2026Zeyi Shao, Haowen Hua, Jiaxin Zhang +3Prompt LearningNoisy-Label Learning

  21. Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels

    Sep 14, 2026Mushir Akhtar, Akarsh J., M. Tanveer +1Class-Imbalanced LearningLong-Tail Learning

  22. OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise

    Sep 13, 2026Sina Gholami, Abdulmoneam Ali, Tania Haghighi +8Federated LearningNoisy-Label Learning

  23. Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings

    Sep 11, 2026Akihisa Shitara, Yoichi OchiaiNoisy-Label LearningRobust Loss Functions

  24. Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels

    Aug 31, 2026Elena Merdjanovska, Jonas Golde, Alan AkbikNamed Entity RecognitionLLM-Assisted Annotation

  25. Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction

    Aug 30, 2026João L. P. Santana, Filipe R. CordeiroNoisy-Label LearningClassification

  26. Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Based Granular Ball Computing

    Aug 12, 2026Ziqiang Li, Yun Liu, Gouhei TanakaDynamic Time WarpingTime Series Classification

  27. Sparse and robust geometric twin support vector machine via asymmetric RoBoSS loss function

    Aug 12, 2026Kai Qi, Xinji Huang, Hongchun WangNoisy-Label LearningRobust Loss Functions