BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jingfeng, Song, Bo, Wang, Haohan, Han, Bo, Liu, Tongliang, Liu, Lei, Sugiyama, Masashi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913230055538688
author Zhang, Jingfeng
Song, Bo
Wang, Haohan
Han, Bo
Liu, Tongliang
Liu, Lei
Sugiyama, Masashi
author_facet Zhang, Jingfeng
Song, Bo
Wang, Haohan
Han, Bo
Liu, Tongliang
Liu, Lei
Sugiyama, Masashi
contents Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to instance-dependent noises. In this paper, we introduce a novel label noise type called BadLabel, which can significantly degrade the performance of existing LNL algorithms by a large margin. BadLabel is crafted based on the label-flipping attack against standard classification, where specific samples are selected and their labels are flipped to other labels so that the loss values of clean and noisy labels become indistinguishable. To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable. Once we select a small set of (mostly) clean labeled data, we can apply the techniques of semi-supervised learning to train the model accurately. Empirically, our experimental results demonstrate that existing LNL algorithms are vulnerable to the newly introduced BadLabel noise type, while our proposed robust LNL method can effectively improve the generalization performance of the model under various types of label noise. The new dataset of noisy labels and the source codes of robust LNL algorithms are available at https://github.com/zjfheart/BadLabels.
format Preprint
id arxiv_https___arxiv_org_abs_2305_18377
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
Zhang, Jingfeng
Song, Bo
Wang, Haohan
Han, Bo
Liu, Tongliang
Liu, Lei
Sugiyama, Masashi
Machine Learning
Computer Vision and Pattern Recognition
Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to instance-dependent noises. In this paper, we introduce a novel label noise type called BadLabel, which can significantly degrade the performance of existing LNL algorithms by a large margin. BadLabel is crafted based on the label-flipping attack against standard classification, where specific samples are selected and their labels are flipped to other labels so that the loss values of clean and noisy labels become indistinguishable. To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable. Once we select a small set of (mostly) clean labeled data, we can apply the techniques of semi-supervised learning to train the model accurately. Empirically, our experimental results demonstrate that existing LNL algorithms are vulnerable to the newly introduced BadLabel noise type, while our proposed robust LNL method can effectively improve the generalization performance of the model under various types of label noise. The new dataset of noisy labels and the source codes of robust LNL algorithms are available at https://github.com/zjfheart/BadLabels.
title BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.18377