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.
@article{arxiv.2603.13894,
title = {Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels},
author = {Zhanhui Lin and Yanlin Liu and Sanping Zhou},
journal= {arXiv preprint arXiv:2603.13894},
year = {2026}
}