Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lin, Zhanhui, Liu, Yanlin, Zhou, Sanping
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908886196289536
author Lin, Zhanhui
Liu, Yanlin
Zhou, Sanping
author_facet Lin, Zhanhui
Liu, Yanlin
Zhou, Sanping
contents Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning techniques, but they often exhibit low utilization efficiency of noisy samples and incur high computational costs. In this paper, we propose a self-training label correction framework using decoupled bilevel optimization, where a classifier and neural correction function co-evolve. Leveraging a small clean dataset, our method employs noisy posterior simulation and intermediate features to transfer ground-truth knowledge, forming a closed-loop feedback system that prevents error amplification. Theoretical guarantees underpin the stability of our approach, and extensive experiments on benchmark datasets like CIFAR and Clothing1M confirm state-of-the-art performance with reduced training time, highlighting its practical applicability for learning from noisy labels.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13894
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels
Lin, Zhanhui
Liu, Yanlin
Zhou, Sanping
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning techniques, but they often exhibit low utilization efficiency of noisy samples and incur high computational costs. In this paper, we propose a self-training label correction framework using decoupled bilevel optimization, where a classifier and neural correction function co-evolve. Leveraging a small clean dataset, our method employs noisy posterior simulation and intermediate features to transfer ground-truth knowledge, forming a closed-loop feedback system that prevents error amplification. Theoretical guarantees underpin the stability of our approach, and extensive experiments on benchmark datasets like CIFAR and Clothing1M confirm state-of-the-art performance with reduced training time, highlighting its practical applicability for learning from noisy labels.
title Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13894