• Home
  • Search
  • Analyzing Deep Neural Networks with Noisy Labels
  • Cite Icon2
  • https://doi.org/10.1109/bigcomp48618.2020.00012Copy DOI Icon

Analyzing Deep Neural Networks with Noisy Labels

  • Feb 1, 2020
  • Chan Lim +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Training deep neural networks (DNNs) with noisy labels is a fundamental problem in achieving generalization in DNNs. Recent studies mainly adopt sample selection in which the samples with small losses are regarded as clean ones, based on the findings that DNNs tend to learn simple and easy patterns first, and then gradually memorize all data. In this paper, we further investigate the sample selection by observing the loss distribution of training samples with clean and noisy labels. In experimental results, we found that the loss distributions with clean and noisy samples are different at the early stage, and gradually converge into similar distributions. Besides, this phenomenon is notably different depending on the datasets and noise types, such as symmetric and pair. Based on these findings, we argue that the sample selection method should consider an early stopping condition in learning DNNs with noisy labels.

Similar Papers
  • Research Article
  • Citations11

Learning with noisy labels using collaborative sample selection and contrastive semi-supervised learning

  • Apr 27, 2024
  • Knowledge-Based Systems
  • Qing Miao +6
  • Video Transcripts

P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions

  • Dec 29, 2020
  • Underline Science Inc.
  • Qihao Zhao
  • Conference Article
  • Citations4

P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions

  • Jan 10, 2021
  • Wei Hu +3
  • Research Article
  • Citations9

P-DIFF+: Improving learning classifier with noisy labels by Noisy Negative Learning loss

  • Aug 02, 2021
  • Neural Networks
  • Qihao Zhao +3
  • Research Article
  • Citations4

Agree to Disagree: Robust Anomaly Detection with Noisy Labels

  • Feb 10, 2025
  • Proceedings of the ACM on Management of Data
  • Dennis M Hofmann +6
  • PDF
  • Research Article
  • Citations3

Separating hard clean samples from noisy samples with samples’ learning risk for DNN when learning with noisy labels

  • Mar 01, 2024
  • Complex & Intelligent Systems
  • Lihui Deng +5
  • Research Article

Outlier-trimmed dual-interval smoothing loss for sample selection in learning with noisy labels.

  • Nov 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Senyu Hou +4
  • Research Article
  • Citations11

Penalty based robust learning with noisy labels

  • Feb 16, 2022
  • Neurocomputing
  • Kyeongbo Kong +5
  • Research Article
  • Citations8

Class-Independent Regularization for Learning with Noisy Labels

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Rumeng Yi +3
  • Conference Article
  • Citations2

Identifying the Training Stop Point with Noisy Labeled Data

  • Dec 01, 2020
  • Sree Ram Kamabattula +3
  • Conference Article

A Robust Learning Framework Using Self-supervised Learning for Learning with Noisy Labels

  • Oct 18, 2022
  • Ryota Higashimoto +2
  • PDF
  • Research Article
  • Citations7

Training Robust Deep Neural Networks on Noisy Labels Using Adaptive Sample Selection With Disagreement

  • Jan 01, 2021
  • IEEE Access
  • Hiroshi Takeda +2
  • PDF
  • Research Article
  • Citations4

CRAS: Curriculum Regularization and Adaptive Semi-Supervised Learning with Noisy Labels

  • Jan 31, 2024
  • Applied Sciences
  • Ryota Higashimoto +2
  • Conference Article
  • Citations3

TSS-Net: two-stage with sample selection and semi-supervised net for deep learning with noisy labels

  • Jan 13, 2023
  • Xin Lyu +6
  • Conference Article

MixNN: Combating Noisy Labels in Deep Learning by Mixing with Nearest Neighbors

  • Dec 15, 2021
  • Yangdi Lu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.