• Home
  • Search
  • BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning.
  • Open Access IconOpen Access
  • Cite Icon29
  • https://doi.org/10.1109/tpami.2024.3355425Copy DOI Icon

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

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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.

Similar Papers
  • Research Article
  • Citations1

Graph Neural Networks with Coarse- and Fine-Grained Division for mitigating label noise and sparsity.

  • Jul 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Shuangjie Li +5
  • PDF
  • Research Article
  • Citations2

Uncertainty is not sufficient for identifying noisy labels in training data for binary segmentation of building footprints

  • Jan 10, 2023
  • Frontiers in Remote Sensing
  • Hannah Ulman +2
  • Research Article
  • Citations702

Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis.

  • Jun 20, 2020
  • Medical image analysis
  • Davood Karimi +3
  • Conference Article
  • Citations173

Distilling Effective Supervision From Severe Label Noise

  • Jun 01, 2020
  • Zizhao Zhang +4
  • Research Article
  • Citations15

Multi-category classification with label noise by robust binary loss

  • Jan 19, 2022
  • Neurocomputing
  • Defu Liu +4
  • Conference Article
  • Citations378

Iterative Learning with Open-set Noisy Labels

  • Jun 01, 2018
  • Yisen Wang +6
  • Research Article
  • Citations70

Robust Medical Image Classification From Noisy Labeled Data With Global and Local Representation Guided Co-Training.

  • Jun 01, 2022
  • IEEE Transactions on Medical Imaging
  • Cheng Xue +4
  • Conference Article
  • Citations7

Graph-Based Self-Learning for Robust Person Re-identification

  • Jan 01, 2023
  • Yuqiao Xian +4
  • Research Article
  • Citations12

Dense prediction of label noise for learning building extraction from aerial drone imagery

  • Oct 01, 2021
  • International Journal of Remote Sensing
  • Nahian Ahmed +3
  • Conference Article
  • Citations14

Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels

  • Jan 01, 2023
  • Brandon Smart +1
  • Conference Article
  • Citations1132

Learning from massive noisy labeled data for image classification

  • Jun 01, 2015
  • Tong Xiao +4
  • PDF
  • Research Article

The fuzzy support vector data description based on tightness for noisy label detection

  • Mar 04, 2024
  • Complex & Intelligent Systems
  • Xiaoying Wu +2
  • PDF
  • Research Article
  • Citations9

Deep Learning Network Intensification for Preventing Noisy-Labeled Samples for Remote Sensing Classification

  • Apr 27, 2021
  • Remote Sensing
  • Chuang Lin +6
  • Conference Article
  • Citations5

Adaptive Contrastive Learning for Learning Robust Representations under Label Noise

  • Oct 26, 2023
  • Zihao Wang +4
  • Research Article
  • Citations46

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Tom Burgert +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.