ACD-U: Asymmetric co-teaching with machine unlearning for robust learning with noisy labels

TL;DR

ACD-U introduces an asymmetric co-teaching framework with machine unlearning that leverages different model architectures and post-hoc error correction to improve robustness against noisy labels in deep learning.

Contribution

It proposes a novel asymmetric co-teaching method combining CLIP-pretrained vision Transformers and CNNs with machine unlearning for effective noisy label correction.

Findings

Achieves state-of-the-art results on noisy datasets.

Effectively mitigates confirmation bias in noisy label learning.

Performs well in high-noise and instance-dependent noise scenarios.

Abstract

Deep neural networks are prone to memorizing incorrect labels during training, which degrades their generalizability. Although recent methods have combined sample selection with semi-supervised learning (SSL) to exploit the memorization effect -- where networks learn from clean data before noisy data -- they cannot correct selection errors once a sample is misclassified. To overcome this, we propose asymmetric co-teaching with different architectures (ACD)-U, an asymmetric co-teaching framework that uses different model architectures and incorporates machine unlearning. ACD-U addresses this limitation through two core mechanisms. First, its asymmetric co-teaching pairs a contrastive language-image pretraining (CLIP)-pretrained vision Transformer with a convolutional neural network (CNN), leveraging their complementary learning behaviors: the pretrained model provides stable predictions, whereas the CNN adapts throughout training. This asymmetry, where the vision Transformer is trained only on clean samples and the CNN is trained through SSL, effectively mitigates confirmation bias. Second, selective unlearning enables post-hoc error correction by identifying incorrectly memorized samples through loss trajectory analysis and CLIP consistency checks, and then removing their influence via Kullback--Leibler divergence-based forgetting. This approach shifts the learning paradigm from passive error avoidance to active error correction. Experiments on synthetic and real-world noisy datasets, including CIFAR-10/100, CIFAR-N, WebVision, Clothing1M, and Red Mini-ImageNet, demonstrate state-of-the-art performance, particularly in high-noise regimes and under instance-dependent noise. The code is publicly available at https://github.com/meruemon/ACD-U.