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

Abstract

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.

References in corpus (18)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Learning to Reweight Examples for Robust Deep Learning
• Classification with Noisy Labels by Importance Reweighting
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• A Closer Look at Memorization in Deep Networks
• Dimensionality-Driven Learning with Noisy Labels
• Are Anchor Points Really Indispensable in Label-Noise Learning?
• Masking: A New Perspective of Noisy Supervision
• How does Disagreement Help Generalization against Label Corruption?
• Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
• Part-dependent Label Noise: Towards Instance-dependent Label Noise
• Mixture Proportion Estimation via Kernel Embedding of Distributions
• Robustness of Conditional GANs to Noisy Labels
• SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
• Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels
• On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
• Transfer Learning with Label Noise
• Generalization Bounds for Neural Networks via Approximate Description Length

Cited by in corpus (10)

• Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
• Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives
• Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
• One-Step Abductive Multi-Target Learning with Diverse Noisy Samples and Its Application to Tumour Segmentation for Breast Cancer
• Variational Rectification Inference for Learning with Noisy Labels
• Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
• Validation of the Practicability of Logical Assessment Formula for Evaluations with Inaccurate Ground-Truth Labels: An Application Study on Tumour Segmentation for Breast Cancer
• GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence
• Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
• Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography