Data to 7 Oct 2026

Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning

arXiv 2006.07805 ↗First posted 14 Jun 2020cs.LG stat.MLcited by 142

Not on the map. Why?

Abstract (arXiv)

The transition matrix, denoting the transition relationship from clean labels to noisy labels, is essential to build statistically consistent classifiers in label-noise learning. Existing methods for estimating the transition matrix rely heavily on estimating the noisy class posterior. However, the estimation error for noisy class posterior could be large due to the randomness of label noise, which would lead the transition matrix to be poorly estimated. Therefore, in this paper, we aim to solve this problem by exploiting the divide-and-conquer paradigm. Specifically, we introduce an intermediate class to avoid directly estimating the noisy class posterior. By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices. We term the proposed method the dual-T estimator. Both theoretical analyses and empirical results illustrate the effectiveness of the dual-T estimator for estimating transition matrices, leading to better classification performances.

Key facts. Cited by 142 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 26; 2023: 33; 2024: 20; 2025: 21; 2026: 12.

142 papers.

Sort:

By area:

2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
2021Breaking the Dilemma of Medical Image-to-image Translationcited by 82
2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49

38 more

2021Robust Long-Tailed Learning under Label Noisecited by 35
2022Identifiability of Label Noise Transition Matrixcited by 34
2022Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guaranteescited by 34
2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
2022Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Featurescited by 27
2023Semi-Supervised Domain Adaptation with Source Label Adaptationcited by 26
2023Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidancecited by 24
2022Few-shot Learning with Noisy Labelscited by 23
2021Understanding Instance-Level Label Noise: Disparate Impacts and Treatmentscited by 22
2022PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learningcited by 21
2022On Learning Contrastive Representations for Learning with Noisy Labelscited by 21
2022Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classificationcited by 21
2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
2022Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-trainingcited by 21
2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
2023Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?cited by 21
2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
2021Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noisecited by 18
2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
2024Label-Noise Robust Diffusion Modelscited by 16
2024CLIPCleaner: Cleaning Noisy Labels with CLIPcited by 16
2021Analysing the Noise Model Error for Realistic Noisy Label Datacited by 14
2021Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimationcited by 13
2021Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficialcited by 13
2023Robust T-Loss for Medical Image Segmentationcited by 13
2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
2021Tackling Instance-Dependent Label Noise via a Universal Probabilistic Modelcited by 12
2021Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classificationcited by 12
2023CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learningcited by 11
2023ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerancecited by 11
2022L2B: Learning to Bootstrap Robust Models for Combating Label Noisecited by 10
2022PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labelscited by 10
2023DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modelingcited by 10
2021Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledgecited by 9
2022BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classificationcited by 9
2022Instance-dependent Label Distribution Estimation for Learning with Label Noisecited by 9

50 most cited of 142 All 142 (JSON)