Combating noisy labels by alleviating the memorization of DNNs to noisy labels

Publication Type

Journal Article

Publication Date

2-2025

Abstract

Data is the essential fuel for deep neural networks (DNNs), and its quality affects the practical performance of DNNs. In real-world training scenarios, the successful generalization performance of DNNs is severely challenged by noisy samples with incorrect labels. To combat noisy samples in image classification, numerous methods based on sample selection and semi-supervised learning (SSL) have been developed, where sample selection is used to provide the supervision signal for SSL, achieving great success in resisting noisy samples. Due to the necessary warm-up training on noisy datasets and the basic sample selection mechanism, DNNs are still confronted with the challenge of memorizing noisy samples. However, existing methods do not address the memorization of noisy samples by DNNs explicitly, which hinders the generalization performance of DNNs. To alleviate this issue, we present a new approach to combat noisy samples. First, we propose a memorized noise detection method to detect noisy samples that DNNs have already memorized during the training process. Next, we design a noise-excluded sample selection method and a noise-alleviated MixMatch to alleviate the memorization of DNNs to noisy samples. Finally, we integrate our approach with the established method DivideMix, proposing Modified-DivideMix. The experimental results on CIFAR-10, CIFAR-100, and Clothing1M demonstrate the effectiveness of our approach.

Keywords

Deep neural networks, image classification. label flipping attack, noisy label learning, sample selection

Discipline

Graphics and Human Computer Interfaces | OS and Networks | Theory and Algorithms

Publication

IEEE Transactions on Multimedia

Volume

27

Issue

1

First Page

597

Last Page

609

ISSN

1520-9210

Identifier

10.1109/TMM.2024.3521722

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TMM.2024.3521722

This document is currently not available here.

Share

COinS