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

TL;DR

This paper introduces a self-training framework with closed-loop label correction for deep neural networks trained on noisy labels, achieving state-of-the-art results efficiently.

Contribution

It proposes a novel bilevel optimization-based self-training method that uses a small clean dataset and closed-loop feedback to correct noisy labels effectively.

Findings

Achieves state-of-the-art performance on CIFAR and Clothing1M datasets.

Reduces training time compared to existing methods.

Provides theoretical guarantees for stability.

Abstract

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.