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

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark
May 25, 2026Xu Yao, Siyuan Zhou, Zhenbo Wu +6Learning with Noisy Labels Anomaly Detection
Shanghai University of Finance and Economics · Ant Group · Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics
TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models
May 22, 2026Rongye Ye, Lun Li, Zheng Luo +3Learning with Noisy Labels Knowledge Distillation
National Genomics Data Center, China National Center for Bioinformation, Beijing 100101, China · Beijing Institute of Genomics, Chinese Academy of Sciences, Beijing 100101, China · University of Chinese Academy of Sciences, Beijing 100049, China +1
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
May 22, 2026Mengke Li, Haiquan Ling, Lihao Chen +3Class-Imbalanced Learning Learning with Noisy Labels
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China
LQ-rPPG: A Label-Quantized Coarse-to-Fine Learning Framework for Remote Physiological Measurement
May 22, 2026Jun Seong Lee, Samyeul Noh, Changki Sung +1Remote Photoplethysmography Learning with Noisy Labels
Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon 34129, Republic of Korea · School of Electrical Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, Republic of Korea
GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
May 20, 2026Ningkang Peng, Jingyang Mao, Xiaoqian Peng +4Geometric Representation Learning Manifold Learning
Nanjing Normal University Nanjing, China · Nanjing University of Chinese Medicine Nanjing, China
Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
May 20, 2026Jingyang Mao, Ningkang Peng, Yanhui GuClassification Learning with Noisy Labels
Nanjing Normal University Nanjing, China
Efficient and Noise-Tolerant PAC Learning of Multiclass Linear Classifiers
May 18, 2026Rita Adhikari, Shiwei ZengMulticlass Classification Classification
Augusta University
Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
May 18, 2026Linyu Liu, Pinyan LuNeural Network Generalization Neural Network Memorization
1Taylor Lab, Huawei Technologies Co., Ltd. · 2Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
May 18, 2026Ningkang Peng, Jingyang Mao, Runhan Zhou +2Learning with Noisy Labels OOD Detection
Nanjing Normal University
MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
May 15, 2026Dayong RenLearning with Noisy Labels
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China.
Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
May 15, 2026Tan-Ha Mai, Chao-Kai Chiang, Han-Hwa Shih +3Multiclass Classification Weakly Supervised Learning
1National Taiwan University · 3RIKEN Center for Advanced Intelligence Project · 2The University of Tokyo
Learning with Semantic Priors: Stabilizing Point-Supervised Infrared Small Target Detection via Hierarchical Knowledge Distillation
May 14, 2026Yuanhang Yao, Ping Qian, Zhu Liu +2Infrared Small Target Detection Object Detection
School of Software Technology, Dalian University of Technology, China
HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
May 12, 2026Ningkang Peng, Jingyang Mao, Qianfeng Yu +3Learning with Noisy Labels
Nanjing Normal University Nanjing, China · Nanjing University of Chinese Medicine Nanjing, China
Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation
May 11, 2026Inhyuk Park, Doohyun ParkNoisy-Label Learning Learning with Noisy Labels
VUNO Inc.
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
May 11, 2026Danhui Zhang, Zhe Wang, Qing Qing +6Replay-Based Continual Learning Flow-Based Generative Modeling
Jilin University · Adelaide University · RMIT University +1
WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records
May 10, 2026Ruan Dong, Yuanyun Zhang, Shi LiHealthcare Multi-View Learning
University of Science and Technology of China · Columbia University
Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
May 7, 2026Aditya Parikh, Stella Frank, Sneha Das +1Image Segmentation Algorithmic Fairness
Department of Applied Mathematics and Computer Science Technical University of Denmark
Architecture-agnostic Lipschitz-constant Bayesian header and its application to resolve semantically proximal classification errors with vision transformers
May 7, 2026Frederik Schäfer, Luis Mandl, Lars Kälber +1Bayesian Neural Networks Vision Transformer
Institute of Structural Mechanics and Dynamics in Aerospace Engineering, University of Stuttgart · Rockwell Collins Deutschland GmbH · Department of Hepatobiliary Surgery and Visceral Transplantation, University of Leipzig Medical Center
ITBoost: Information-Theoretic Trust for Robust Boosting
May 6, 2026Ye Su, Longlong Zhao, Diego Garcia-Gil +4Gradient-Boosted Decision Trees Ensemble Learning
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Department of Software Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada +1
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
May 3, 2026Kumar Shubham, Pavan Karjol, Kiran M K +1Training Data Selection Learning with Noisy Labels
Indian Institute of Science, Bangalore, India
Learning Coarse-to-Fine Osteoarthritis Representations under Noisy Hierarchical Labels
May 1, 2026Tongxu ZhangHierarchical Classification Hierarchical Representation Learning
The Hong Kong Polytechnic University
Risk-Aware Robust Learning: Reducing Clinical Risk under Label Noise in Medical Image Classification
Apr 26, 2026Maycon R. S. Pereira, Filipe R. CordeiroCost-Sensitive Learning Medical Image Classification
Visual Computing Lab, Departamento de Computac¸˜ao, Universidade Federal Rural de Pernambuco (UFRPE), Brasil
From Noisy Historical Maps to Time-Series Oil Palm Mapping Without Annotation in Malaysia and Indonesia (2020-2024)
Apr 26, 2026Nuttaset Kuapanich, Juepeng Zheng, Bohan Shi +6Remote Sensing Image Segmentation Agricultural Remote Sensing
School of Artificial Intelligence, Sun Yat-Sen University, Zhuhai, China. · National Supercomputing Center in Shenzhen, Shenzhen, China. · Khoury College of Computer Sciences, Northeastern University, Boston, United States of America. +1
An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations
Apr 25, 2026Varun Totakura, Ankita Singh, Yushun Dong +1Human-in-the-Loop Annotation Active Learning
Department of Computer Science Florida State University Tallahassee, FL, USA
Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label
Apr 25, 2026Mengke Li, Haiquan Ling, Yiqun Zhang +2Long-Tail Learning Learning with Noisy Labels
CSSE, Shenzhen University · SCST, Guangdong University of Technology · INFORMATICS, Xiamen University
FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels
Apr 22, 2026Sina Gholami, Abdulmoneam Ali, Tania Haghighi +2Noisy-Label Learning Learning with Noisy Labels
University of North Carolina at Charlotte Charlotte, NC, USA
ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval
Apr 22, 2026Zixu Li, Yupeng Hu, Zhiwei Chen +3Learning with Noisy Labels Machine Unlearning
1Shandong University · 2Harbin Institute of Technology (Shenzhen)
FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning
Apr 21, 2026Abdulmoneam Ali, Ahmed ArafaClustering Noisy-Label Learning
Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, NC 28223, USA
Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval
Apr 21, 2026Zhiheng Fu, Yupeng Hu, Qianyun Yang +3Cross-Modal Alignment Learning with Noisy Labels
Shandong University
Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?
Apr 20, 2026Chengan Che, Chao Wang, Jiayuan Huang +2Surgical Video Understanding Medical VLMs
Visual Understanding Research Group, Department of Informatics, King’s College London, UK

May 25, 2026, cs.LGJ/K move · Enter open · S save

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark

Xu Yao, Siyuan Zhou, Zhenbo Wu, Chaochuan Hou+5

Shanghai University of Finance and Economics · Ant Group · Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics

Learning with Noisy Labels Anomaly Detection

Open paper AskPDF arXiv

Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these directions remain isolated, lacking a unified framework to assess whether they address unique challenges or share fundamental mechanisms. This paper introduces WSADBench, the first benchmark that unifies evaluation across distinct weakly supervised scenarios, benchmarking diverse approaches from specialized WSAD methods to advanced tabular foundation models. WSADBench establishes standardized protocols to evaluate 36 algorithms across 4 modalities by systematically varying label quantity, granularity, and quality, revealing the performance boundaries of various methods. Based on over 700K experiments, WSADBench reveals four critical insights: (i) Strong intrinsic correlations exist between these weak supervision scenarios, challenging the isolation of current research directions. (ii) Specialized WSAD algorithms excel only in extreme label-scarcity regimes but are quickly dominated by tabular foundation models and general classification methods as supervision increases or in OOD scenarios. (iii) Unlabeled data shows inconsistent utility across settings, with marginal gains compared to label refinement. (iv) Models exhibit asymmetric sensitivity to different types of label noise. We release WSADBench as an open-source benchmark with code and datasets to facilitate future WSAD research: https://github.com/SUFE-AILAB/WSADBench.

Momentum

Related topics

Latest papers 101