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

by   Jingfeng Zhang, et al.

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


page 1

page 9

page 12


Contrastive Learning Improves Model Robustness Under Label Noise

Deep neural network-based classifiers trained with the categorical cross...

Towards Robust Learning with Different Label Noise Distributions

Noisy labels are an unavoidable consequence of automatic image labeling ...

Label Noise-Robust Learning using a Confidence-Based Sieving Strategy

In learning tasks with label noise, boosting model robustness against ov...

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

Learning with noisy labels is a practically challenging problem in weakl...

Hard Sample Aware Noise Robust Learning for Histopathology Image Classification

Deep learning-based histopathology image classification is a key techniq...

Regularly Truncated M-estimators for Learning with Noisy Labels

The sample selection approach is very popular in learning with noisy lab...

Generating the Ground Truth: Synthetic Data for Label Noise Research

Most real-world classification tasks suffer from label noise to some ext...

Please sign up or login with your details

Forgot password? Click here to reset