• Home
  • Search
  • P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
  • https://doi.org/10.48448/b1nd-m843Copy DOI Icon

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

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over- fit on these noisy labels due to its high capability. In this paper, we present a very simple but effective training paradigm called P-DIFF, which can train DNN classifiers but obviously alleviate the adverse impact of noisy labels. Our proposed probability difference distribution implicitly reflects the probability of a training sample to be clean, then this probability is employed to re-weight the corresponding sample during the training process. P-DIFF can also achieve good performance even without prior knowledge on the noise rate of training samples. Experiments on benchmark datasets also demonstrate that P-DIFF is superior to the state-of-the-art sample selection methods.

Similar Papers
  • 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
  • Conference Article
  • Citations2

Analyzing Deep Neural Networks with Noisy Labels

  • Feb 01, 2020
  • Chan Lim +2
  • 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
  • Research Article
  • Citations82

Growing random forest on deep convolutional neural networks for scene categorization

  • Oct 17, 2016
  • Expert Systems with Applications
  • Shuang Bai
  • PDF
  • Research Article
  • Citations1

Self-Augmentation Based on Noise-Robust Probabilistic Model for Noisy Labels

  • Jan 01, 2022
  • IEEE Access
  • Byoung Woo Park +2
  • Research Article

Meta-Data-Guided Robust Deep Neural Network Classification with Noisy Label

  • Feb 16, 2025
  • Applied Sciences
  • Jie Lu +4
  • Conference Article
  • Citations1000

Symmetric Cross Entropy for Robust Learning With Noisy Labels

  • Oct 01, 2019
  • Yisen Wang +5
  • Research Article
  • Citations10

Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation

  • Jun 28, 2022
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Yaoru Luo +3
  • PDF
  • Research Article
  • Citations30

Utilization of Random Forest and Deep Learning Neural Network for Predicting Factors Affecting Perceived Usability of a COVID-19 Contact Tracing Mobile Application in Thailand “ThaiChana”

  • May 17, 2022
  • International Journal of Environmental Research and Public Health
  • Ardvin Kester S Ong +9
  • PDF
  • Research Article

Gradient Agreement Hinders the Memorization of Noisy Labels

  • Jan 31, 2023
  • Applied Sciences
  • Shaotian Yan +3
  • Conference Article
  • Citations1

Adaptive sample selection with joint loss for medical image classification under label noise

  • Jan 15, 2025
  • Tongqing Xue +2
  • Conference Article

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks

  • Jan 01, 2016
  • Mostafa Shahin +1
  • Research Article
  • Citations17

Early detection of infestation by mustard aphid, vegetable thrips and two-spotted spider mite in bok choy with deep neural network (DNN) classification model using hyperspectral imaging data

  • Apr 04, 2024
  • Computers and Electronics in Agriculture
  • Derrick Nguyen Hoang Danh +5
  • Conference Article
  • Citations2

DNN Classifier and Decision Tree-Based Novel Methodology for Analyzing Road Accidents

  • Sep 01, 2019
  • Shehani N Ariyathilake +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.