• Home
  • Search
  • Separating Noisy Samples From Tail Classes for Long-Tailed Image Classification With Label Noise.
  • Cite Icon27
  • https://doi.org/10.1109/tnnls.2023.3291695Copy DOI Icon

Separating Noisy Samples From Tail Classes for Long-Tailed Image Classification With Label Noise.

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

Most existing methods that cope with noisy labels usually assume that the classwise data distributions are well balanced. They are difficult to deal with the practical scenarios where training samples have imbalanced distributions, since they are not able to differentiate noisy samples from tail classes' clean samples. This article makes an early effort to tackle the image classification task in which the provided labels are noisy and have a long-tailed distribution. To deal with this problem, we propose a new learning paradigm which can screen out noisy samples by matching between inferences on weak and strong data augmentations. A leave-noise-out regularization (LNOR) is further introduced to eliminate the effect of the recognized noisy samples. Besides, we propose a prediction penalty based on the online classwise confidence levels to avoid the bias toward easy classes which are dominated by head classes. Extensive experiments on five datasets including CIFAR-10, CIFAR-100, MNIST, FashionMNIST, and Clothing1M demonstrate that the proposed method outperforms the existing algorithms for learning with long-tailed distribution and label noise.

Similar Papers
  • Research Article

A Progressive Deep Neural Network Training Method for Image Classification with Noisy Labels

  • Dec 12, 2022
  • Applied Sciences
  • Xuguo Yan +3
  • 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
  • Research Article
  • Citations2

Cyclic Learning Rate-Based Co-Training for Image Classification With Noisy Labels

  • Jan 01, 2025
  • IEEE Access
  • Ying Zheng +6
  • PDF
  • Research Article
  • Citations1

An Improved Heteroscedastic Modeling Method for Chest X-ray Image Classification with Noisy Labels

  • May 04, 2023
  • Algorithms
  • Qingji Guan +2
  • Research Article
  • Citations4

Meta-probability Weighting for Improving Reliability of DNNs to Label Noise.

  • Apr 01, 2023
  • IEEE journal of biomedical and health informatics
  • Zhen Wang +4
  • Conference Article
  • Citations33

ProMix: Combating Label Noise via Maximizing Clean Sample Utility

  • Aug 01, 2023
  • Ruixuan Xiao +6
  • Research Article

FedEBM: Robust graph federated learning via energy-based model.

  • May 28, 2026
  • Neural networks : the official journal of the International Neural Network Society
  • Jiayu Wang +4
  • PDF
  • Research Article

INNT: Restricting Activation Distance to Enhance Consistency of Visual Interpretation in Neighborhood Noise Training

  • Nov 23, 2023
  • Electronics
  • Xingyu Wang +5
  • Research Article
  • Citations12

Co-Learning Meets Stitch-Up for Noisy Multi-label Visual Recognition.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Chao Liang +3
  • Conference Article
  • Citations1

Distribution Mining and Noise Correction for Facial Expression Recognition

  • Apr 19, 2024
  • Hailan Huang +1
  • Book Chapter
  • Citations1

CCLM: Class-Conditional Label Noise Modelling

  • Jan 01, 2023
  • Albert Tatjer +3
  • Research Article
  • Citations27

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Jichang Li +4
  • Research Article
  • Citations102

LongReMix: Robust learning with high confidence samples in a noisy label environment

  • Sep 02, 2022
  • Pattern Recognition
  • Filipe R Cordeiro +4
  • Research Article
  • Citations6

Mitigating data imbalance and noise: A divergence-based approach with enhanced sample selection

  • Jul 26, 2024
  • Neurocomputing
  • Xuan Chen +5
  • Research Article
  • Citations10

TBC-MI : Suppressing noise labels by maximizing cleaning samples for robust image classification

  • Jun 12, 2024
  • Information Processing and Management
  • Yanhong Li +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.