Noisy Labels

Follow this topic Ask about this topic

Recent momentum

-29%

5 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Noisy Labels.

Period ending 2026-09-07

2 new papers

A weekly snapshot of new work published in Noisy Labels.

70 papers

Latest in Noisy Labels

Browse all topics →

Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
Sep 14, 2026Mushir Akhtar, Akarsh J., M. Tanveer +1Noisy Labels Extreme Class Imbalance
Empirical Evaluation of Data Poisoning Attacks in Supervised Learning
Sep 10, 2026Toshif Khan, Muhammad AbusaqerData Poisoning Noisy Labels
The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations
Sep 3, 2026Emanuele Cardinale, Marco Proietti, Alessandro Cacciatore +3Noisy Labels Keypoint Detection
Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels
Aug 31, 2026Elena Merdjanovska, Jonas Golde, Alan AkbikNamed-Entity Recognition Noisy Labels
Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction
Aug 30, 2026João L. P. Santana, Filipe R. CordeiroNoisy Labels Machine Unlearning
Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Based Granular Ball Computing
Aug 12, 2026Ziqiang Li, Yun Liu, Gouhei TanakaGranular-Ball Computing Time-Series Classification
Zero-OVCD: Bridging Training-Free Foundation Models and Pseudo-Label Learning for Open-Vocabulary Change Detection
Aug 12, 2026Daifeng Peng, Yuanke Peng, Haiyan GuanChange Detection Pseudo-Labeling
Dual-Primal Graph VAEs for Noisy Label Aggregation
Aug 11, 2026Patrick Stinson, Nikolaus KriegeskorteNoisy Labels Variational Autoencoder
Triple Expert Learning from Noisy Labels for Semi-Supervised Vision Foundation Model Adaptation
Aug 10, 2026Xuanyu Liu, Zheng Fang, Hongyang He +2Vision-Language Model Adaptation Noisy Labels
Towards Trustworthy Hypergraph Neural Networks under Label Noise
Aug 5, 2026Mengyao Zhou, Zhiheng Zhou, Xiao Han +1Hypergraphs Noisy Labels
LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
Aug 4, 2026Abhishek Moturu, Babak Taati, Anna GoldenbergNoisy Labels Medical Imaging Datasets
Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning
Aug 4, 2026Wenxiao Fan, Kan LiNoisy Labels Noise-Aware
XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
Jul 26, 2026Chengqi Li, Yangdi Lu, Zhihao Shi +3Noisy Labels Semi-Supervised Learning
Robust Conformalized Selection with Noisy Responses
Jul 25, 2026Chengyao Yu, Hongxin Wei, Bingyi JingFalse Discovery Rate Conformal Calibration
Robust Multi-View Classification under Noisy Supervision via Global Anchor Consensus
Jul 20, 2026Yuliang Yang, Hongzhe Zhang, Huiru WangNoisy Labels Multi-View
Leveraging Dissimilarity Invariance as a Robust Anchor for Learning with Noisy Labels
Jul 20, 2026Wenxiao Fan, Kan LiNoisy Labels Invariance
Robust Losses from Univariate Base Functions for Noisy-Label Learning
Jul 18, 2026Peng Hu, Jianwei MaNoisy Labels Loss Function
Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise
Jul 14, 2026Satwik Bathula, Anand A. JoshiFisher Information Noisy Labels
Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels
Jul 9, 2026Hua Qu, Yifan Li, Xiaodong YuanDirect Preference Optimization Meta-Learning
Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data
Jul 9, 2026Chaewon Lee, Seon-Ho Lee, Chang-Su KimNoisy Labels Noisy Data
FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening
Jul 6, 2026Rai Hisada, Kanji TanakaEfficient Continual Learning Noisy Labels
AdaStop: Cost-Aware Early Stopping for DNN Test Selection
Jul 6, 2026Bonan Shen, Wei-Jung Huang, Xin Liu +2Early Stopping Noisy Labels
A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning
Jul 3, 2026Sushant Dagaji Desale, Rahul Mishra, Ashutosh Kumar SinhaDomain Adaptation Adversarial Transferability
Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection
Jun 29, 2026Mohammad Mahdi Abootorabi, Sina Namazi, Armin Saadat +7Ultrasound Multiple Instance Learning
Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets
Jun 29, 2026Kaifeng Chen, Lechao Cheng, Jiyang Li +6Noisy Labels Reweighting
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System
Jun 27, 2026Thomas Thebaud, Sonal Joshi, Henry Li +4Data Poisoning Noisy Labels
Data Pruning: Redundant, Problematic, and Interdependent Samples
Jun 20, 2026Leon Freese, Marthinus W. TheunissenPruning Noisy Labels
Denoising Implicit Feedback for Cold-start Recommendation
Jun 17, 2026Gaode Chen, Shicheng Wang, Shikun Li +8Recommender Systems Cold-Start
Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise
Jun 17, 2026Mengxiang Hao, Xin Jiang, Xinghao Huang +10Noisy Labels Extreme Class Imbalance
MOLAR: Learning Multimodal Molecular Representations from Noisy Labels
Jun 16, 2026Yingxu Wang, Kunyu Zhang, Nan Yin +2Noisy Labels Multi-Label Classification
Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selection
Jun 15, 2026Markus Bujotzek, Dimitrios Bounias, Stefan Denner +4Noisy Labels Medical Image Segmentation
Neural Bayesian Anomaly Mitigation: A Robust Loss that Doubles as an Unsupervised Contamination Classifier
Jun 15, 2026S. A. K. Leeney, W. J. Handley, H. T. J. Bevins +1Contamination Noisy Labels
Learning Earthquake Wave Arrival Time Picking from Labels with Inaccuracies
Jun 13, 2026Sen Li, Xu Yang, S. Mostafa Mousavi +5Noisy Labels Full Waveform Inversion
Benchmarking Instance-Dependent Label Noise with Controlled Corruptions
Jun 12, 2026Shadman Islam, Agustinus Kristiadi, Mostafa MilaniNoisy Labels Benchmark Datasets
Limits of spectral learning under noise
Jun 11, 2026Sabin Roman, Ljupco Todorovski, Saso Dzeroski +2Coefficients Noisy Labels
A Data-Centric Framework for Detecting and Correcting Corrupted Labels
Jun 10, 2026Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La +3Noisy Labels
Noise-Aware Framework for Correcting Corrupted Labels
Jun 10, 2026Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La +4Noisy Labels Pseudo-Labeling
Learning from almost nothing: How neural networks survive heavy input corruption
Jun 9, 2026Justin Tahmassebpur, Asadullah Bhuiyan, Hyejin Kim +1Noisy Labels Neural Network
Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency
Jun 7, 2026Md Abdullah Al Forhad, Weishi ShiNoisy Labels Human Annotations
An Adaptive Data cleaning Framework for Noisy Label Detection
Jun 5, 2026Chen-Hsuan Fang, Wei-Hsinag Chen, Pin-Hsuan Yu +2Noisy Labels Feature Space
Fraud Type Decomposition and the Observation-Mechanism Taxonomy:Class-Specific Detection Limits in Payment Networks
May 29, 2026Gaurav DhamaFraud Detection Payment Networks
Data filtering methods for training language models
May 28, 2026Egor Shevchenko, Elena BruchesNatural Language Datasets Noisy Labels
Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs
May 27, 2026Safal Thapaliya, Jiatan Huang, Chuxu ZhangNoisy Labels Large Language Model Reliability
From Theory to Decision Rule: Calibrating the Noisy-Label Crossover for Vision-Language Model Weak Supervision Across Three Medical-Imaging Benchmarks
May 23, 2026Bruce Changlong Xu, Jose James, Alexander RyuWeak Supervision Noisy Labels
CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels
May 22, 2026Mengke Li, Haiquan Ling, Lihao Chen +3Noisy Labels Vision-Language Model Adaptation
Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure
May 21, 2026Zitong Li, Haoyu WangNoisy Labels Noise-Aware
GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
May 20, 2026Ningkang Peng, Jingyang Mao, Xiaoqian Peng +4Noisy Labels Out-Of-Distribution Detection
Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label
May 20, 2026Jingyang Mao, Ningkang Peng, Yanhui GuNoisy Labels Pseudo-Labeling
Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework
May 20, 2026Zongyu Li, Xuanyu Liu, Gongce Cao +3Noisy Labels Recommender Systems
Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
May 19, 2026Alexandre Lemire Paquin, Brahim Chaib-Draa, Philippe GiguèreNoisy Labels Loss Function
Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning
May 18, 2026Ba Hoang Anh Nguyen, Viet Cuong TaNoisy Labels Bilevel Optimization
When Accuracy Is Not Enough: Uncertainty Collapse between Noisy Label Learning and Out-of-Distribution Detection
May 18, 2026Ningkang Peng, Jingyang Mao, Runhan Zhou +2Noisy Labels Out-Of-Distribution
Radial-Angular Geometry for Reliable Update Diagnosis in Noisy-Label Learning
May 17, 2026Ningkang Peng, Jingyang Mao, Xiaoqian Peng +2Noisy Labels Fisher Information
MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
May 15, 2026Dayong RenNoisy Labels Wireless Foundation Models
MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing
May 13, 2026Chaokai Wu, Haofu Shi, Ningxuan Ma +2Message Passing Neural Networks Multi-Label Classification
HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
May 12, 2026Ningkang Peng, Jingyang Mao, Qianfeng Yu +3Noisy Labels Noise-Aware
Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation
May 11, 2026Inhyuk Park, Doohyun ParkNoisy Labels Medical Imaging Datasets
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 +1Noisy Labels Self-Supervised Vision Transformers
ITBoost: Information-Theoretic Trust for Robust Boosting
May 6, 2026Ye Su, Longlong Zhao, Diego Garcia-Gil +4Noisy Labels Gradient Boosted Tree
Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise
May 3, 2026Kumar Shubham, Pavan Karjol, Kiran M K +1Noisy Labels High-Dimensional Data

Sep 14, 2026 · cs.LGJ/K move · Enter open · S save

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

Mushir Akhtar, Akarsh J., M. Tanveer, Mohd. Arshad

Department of Mathematics, Indian Institute of Technology Indore, India · Department of Electrical Engineering, Indian Institute of Technology Indore, India

Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule, but can amplify incorrectly labeled minority examples. We introduce BARGE (Bounded Adjustment with Reliability-Guided Embeddings), a single-stage objective combining a bounded, prior-adjusted density-power score with reliability-guided angular geometry. Its classification score is strictly proper in the adjusted probability space and recovers balanced Bayes ordering under clean supervision and the true class prior. Under label contamination, its finite range bounds classification-risk perturbation at a fixed predictor, while its logit gradient redescends when the model confidently contradicts the supplied label. The adjusted target probability also weights class-equal feature compactness, and a one-sided separation term discourages aligned class directions. BARGE requires neither a noise rate nor a transition matrix, uses one network, and leaves inference unchanged. We evaluate it on CIFAR-10, CIFAR-100, and Tiny ImageNet under long-tail and step imbalance, clean labels, and 20% and 40% random incorrect-label replacement. Across 12 clean settings, BARGE ranks second overall and attains the lowest error in four. Under corruption, it achieves the lowest mean balanced error in all six dataset-corruption settings, reducing the six-setting average from 72.32% for the strongest competitor to 70.00%. It also obtains the highest macro-F1 and macro-AUPRC in every corrupted-label setting. Ablations show that class-equal angular compactness improves on the bounded score alone. These results support bounded predictive influence and reliability-guided geometry as complementary mechanisms for imbalanced learning with uncertain labels.

Noisy Labels Extreme Class Imbalance Balanced Learning

Open paper Ask about it PDF