Learning with Noisy Labels

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, down 45% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 101

All topics

Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise
Oct 1, 2026Sung Ho Jo, Seonghwi Kim, Wonsang Yun +1Distribution Shift Robustness Spurious Correlation Robustness
Pohang University of Science and Technology (POSTECH)
A Dual-Track Curation-and-Classification Framework for Resolving Ground-Truth Label Noise in Operational Sentinel-2 Wheat Area Estimation
Sep 29, 2026Kasimali Agharia, Ujjwal Kumar GuptaAgricultural Image Analysis Agricultural Remote Sensing
Space Applications Centre (SAC), Indian Space Research Organisation (ISRO)
Efficient Robust Learning at the Information-Theoretic Limit
Sep 15, 2026Adam R. Klivans, Konstantinos Stavropoulos, Sergei Tikhonov +1Boolean Function Learning Learning with Noisy Labels
UT Austin · Institute for Advanced Study · Aarhus University
Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
Sep 14, 2026Mushir Akhtar, Akarsh J., M. Tanveer +1Class-Imbalanced Learning Long-Tail Learning
Department of Mathematics, Indian Institute of Technology Indore, India · Department of Electrical Engineering, Indian Institute of Technology Indore, India
When Ground-Truth Fidelity Matters: An Orchestrated UAS Framework for Wheat Streak Mosaic Virus Detection Using Vision Transformers and Machine Learning
Sep 14, 2026Dewi Endah Kharismawati, Sandeep Dhakal, Courtney E. McCusker +3Plant Disease Classification Learning with Noisy Labels
Department of Food, Agricultural, and Biological Engineering, The Ohio State University, Columbus, OH, 43210, USA · Corn, Soybean and Wheat Quality Research Unit, USDA Agricultural Research Service, 1680 Madison Ave., Wooster, OH, 44691, USA
An End-to-End Automated Pipeline for Controllable Crack Data Synthesis
Sep 11, 2026Conghui Li, Muxin Pu, Chern Hong Lim +2Synthetic Data Augmentation Learning with Noisy Labels
School of Information Technology, Monash University, Selangor, Malaysia · Department of Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China · School of Engineering, Monash University, Selangor, Malaysia
The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations
Sep 3, 2026Emanuele Cardinale, Marco Proietti, Alessandro Cacciatore +3Human Pose Estimation Learning with Noisy Labels
Department of Engineering and Geology, Università degli Studi “G. d’Annunzio” Chieti-Pescara, Pescara, 65127, Italy · Department of Political Science, Communication and International Relations, University of Macerata, Macerata, 62100, Italy · Laboratory of Computational Oncology, Department of Oncology, KU Leuven, Leuven, 3000, Belgium +3
AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels
Sep 2, 2026Javier Tirado-Garín, Alan Savio Paul, Shuai Chen +5Learning with Noisy Labels Weakly Supervised Learning
I3A, Universidad de Zaragoza · Niantic Spatial · University of Oxford
Camera trap classification with deep learning under ground truth uncertainty
Aug 31, 2026Leonard Hockerts, Peter S. Stewart, Sarthak Arora +1Learning with Noisy Labels Image Classification
School of Mathematics & Statistics, University of Glasgow, Glasgow, G12 8QQ,2026 United Kingdom. · 2Collaborative Earth, Berkeley, California, United States
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 Learning Classification
Department of Computing Universidade Federal Rural de Pernambuco, Brazil
Robust Broad Learning System with Wave Loss for Classification under Data Uncertainty
Aug 30, 2026Mushir Akhtar, A. Varshney, A. Quadir +3Robust Loss Functions Learning with Noisy Labels
Department of Mathematics Indian Institute of Technology Indore
Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements
Aug 18, 2026Naoki Egami, Sooahn ShinSemiparametric Inference Latent Variable Models
Department of Political Science and Statistics and Data Science Center, Massachusetts Institute of Technology, Cambridge, MA 02139 · Department of Political Science, Massachusetts Institute of Technology, Cambridge, MA 02139
Personalized Scorer Modeling: A Learning-Based Framework for Deriving Robust Sleep Stage Labels from Multiple Experts
Aug 12, 2026Seyyed Ali Hoseini, Javad Baseri, Hamid Saadatfar +2Sleep Stage Classification Human-in-the-Loop Annotation
Department of Electrical and Computer Engineering, University of Birjand, Birjand, South Khorasan, Iran
Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision
Aug 12, 2026Shaojie Zhang, Ke ChenClustering Unsupervised Clustering
Department of Computer Science, The University of Manchester, Manchester M13 9PL, U.K.
When Repository Labels Are Not Image-Level Truth: A Supervision Auditing Framework for Chest Radiograph AI
Aug 10, 2026Yesika Alexandra Agudelo-Londoño, Jhon Wilmer Pino-Román, Brahian Carrera Rodríguez +9Chest X-Ray Classification Learning with Noisy Labels
Medical Imaging and AI in Healthcare Research Group, Biosciences Center, SURA, Medellín, Colombia · Universidad de Antioquia, Medellín, Colombia · IBM Research, San Jose, CA, USA +1
Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons
Aug 10, 2026Kaustubh Shivshankar Shejole, Tanish Agarwal, Arpit Agarwal +1Pairwise Preference Learning Reward Modeling
IIT Bombay, Mumbai, India – 400076
Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adaptation
Aug 10, 2026Xuanyu Liu, Zheng Fang, Hongyang He +2Mixture of Experts Vision Foundation Model Adaptation
Department of Computer Science The University of Warwick Coventry, UK · Manifolda.AI London, UK · Institute for Math & AI Wuhan University Wuhan, China
No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers
Aug 9, 2026Subhabrata Majumdar, Anand Deo, Partha Pratim Saha +1Neural Network Generalization Neural Network Robustness
Indian Institute of Management Bangalore · Independent Researcher · Indian Statistical Institute, Kolkata
CONFER: Conflict-Aware Evidence Negotiation for Regime-Calibrated Weak Supervision in Multimodal Emotion Recognition
Aug 8, 2026Bojing Hou, Ruohao Li, Yitong Zhu +2Graph Neural Networks Multimodal Robustness
The Hong Kong University of Science and Technology (Guangzhou)
Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification
Aug 7, 2026M. Sajid, A. Quadir, A. Rahaman +2Ensemble Learning Neural Network Robustness
Indian Institute of Technology Indore, Simrol, Indore, India · Qatar University, Qatar
Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions
Aug 7, 2026Wei Wang, Gang Niu, Masashi SugiyamaWeakly Supervised Learning Learning with Noisy Labels
RIKEN, Tokyo, Japan · The University of Tokyo, Chiba, Japan
Unmasking Removal-Budget Confounding: A Matched Operating-Point Evaluation Framework for Adaptive Data Cleaning
Aug 6, 2026Wei-Hsiang Chen, Pin-Hsuan Yu, Chen-Hsuan Fang +1Training Data Curation Learning with Noisy Labels
Department of Electrical Engineering, National Taiwan Ocean Univ., Keelung City, Taiwan · AI Research Center, National Taiwan Ocean Univ., Keelung City, Taiwan.
Towards Trustworthy Hypergraph Neural Networks under Label Noise
Aug 5, 2026Mengyao Zhou, Zhiheng Zhou, Xiao Han +1Graph Structure Learning Hypergraph Neural Networks
Academy of Mathematics and Systems Science, Chinese Academy of Sciences and also with the University of Chinese Academy of Sciences, Beijing 100190, China · School of Mathematics and Statistics, Shandong University, Weihai, Shandong 264209, China · School of Artificial Intelligence, Beihang University, Beijing 100191,China
LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
Aug 4, 2026Abhishek Moturu, Babak Taati, Anna GoldenbergMedical Image Classification Noisy-Label Learning
Department of Computer Science University of Toronto The Hospital for Sick Children UHN KITE Research Institute T-CAIREM Vector Institute · Department of Computer Science Institute of Biomedical Engineering University of Toronto Rehabilitation Sciences Institute UHN KITE Research Institute Vector Institute · Department of Computer Science Department of Laboratory Medicine and Pathobiology University of Toronto The Hospital for Sick Children T-CAIREM Vector Institute
XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
Jul 26, 2026Chengqi Li, Yangdi Lu, Zhihao Shi +3Noisy-Label Learning Learning with Noisy Labels
Department of Computing and Software, McMaster University · Département de génie logiciel et TI, École de Technologie Supérieure
Robust Conformalized Selection with Noisy Responses
Jul 25, 2026Chengyao Yu, Hongxin Wei, Bingyi JingSelective Prediction FDR Control
Department of Statistics and Data Science Southern University of Science and Technology Shenzhen 518055, China · School of Artificial Intelligence The Chinese University of Hong Kong, Shenzhen Shenzhen Loop Area Institute Shenzhen 518172, China
GLI-AL: A Multi-Modal Glioma MRI Label Resource with Unified Anatomy-Lesion Labels
Jul 24, 2026Xingyu Xiang, Shuang Hao, Fan Wang +2Medical Image Segmentation Learning with Noisy Labels
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China · Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an, China · Research Center for Intelligent Medical Equipment and Devices (IMED), Xi’an Jiaotong University, Xi’an 710049, China
Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning
Jul 23, 2026Zhihua Xu, Zhijing Yang, Yufeng Yang +1Contrastive Learning Multi-Label Classification
aSun Yat-Sen University, Guangzhou, 510006, GuangDong, China · bGuangdong University of Technology, Guangzhou, 510006, GuangDong, China
OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation
Jul 21, 2026Yuze Dai, Zhihan Zhang, Yan Zhao +6Text-Attributed Graph Learning Learning with Noisy Labels
Beijing Institute of Technology
Robust Multi-View Classification under Noisy Supervision via Global Anchor Consensus
Jul 20, 2026Yuliang Yang, Hongzhe Zhang, Huiru WangMulti-View Learning Noisy-Label Learning
College of Science, Beijing Forestry University, Beijing 100083, China · School of Software, North University of China, Taiyuan, Shanxi 030051, China

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

Sung Ho Jo, Seonghwi Kim, Wonsang Yun, Minwoo Chae

Pohang University of Science and Technology (POSTECH)

Distribution Shift Robustness Spurious Correlation Robustness Learning with Noisy Labels Optimal Transport

Open paper AskPDF arXiv

Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely on shortcut features that fail to generalize across subgroups. A recent line of work mitigates this issue by using loss-based signals to identify informative samples, but these signals can become severely distorted under label noise: mislabeled samples may also incur large losses and contaminate subsequent reweighting or retraining. Despite its practical importance, this intersection remains largely underexplored. We propose POTER, a reweighting framework based on optimal transport that derives sample importance from the transport geometry between the training distribution and a reference distribution constructed from limited validation group annotations. By measuring alignment at the individual-sample level rather than relying on loss, POTER downweights mislabeled or strongly bias-aligned samples while assigning higher importance to samples better aligned with the reference distribution. In addition, POTER requires only a single ERM training stage, moving beyond the retraining paradigm common in recent work. Across standard benchmarks and noisy-label settings, POTER achieves state-of-the-art worst-group accuracy, including cases where label corruption is concentrated within minority subgroups.

Momentum

Related topics

Latest papers 101