• Home
  • Search
  • Meta-Data-Guided Robust Deep Neural Network Classification with Noisy Label
  • https://doi.org/10.3390/app15042080Copy DOI Icon

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

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

Deep neural network (DNN)-based classifiers have witnessed great applications in various fields. Unfortunately, the labels of real-world training data are commonly noisy, i.e., the labels of a large percentage of training samples are wrong, which negatively affects the performance of a trained DNN classifier during inference. Therefore, it is challenging to practically formulate a robust DNN classifier using noisy labels in training. To address the above issue, our work designs an effective architecture for training the robust DNN classifier with noisy labels, named a cross dual-branch network guided by meta-data on a single side (CoNet-MS), in which a small amount of clean data, i.e., meta-data, are used to guide the training of the DNN classifier. Specifically, the contributions of our work are threefold. First, based on the principle of small loss, each branch using the base classifier as a neural network module infers partial samples with pseudo-clean labels, which are then used for training another branch through a cross structure that can alleviate the cumulative impact of mis-inference. Second, a meta-guided module is designed and inserted into the single branch, e.g., the upper branch, which dynamically adjusts the ratio between the observed label and the pseudo-label output by the classifier in the loss function for each training sample. The asymmetric dual-branch design makes two classifiers diverge, which facilitates them to filter different types of noisy labels and avoid confirmation bias in self-training. Finally, thorough experiments demonstrate that the trained classifier with our proposal is more robust: the accuracy of the classifier trained with our proposed CoNet-MS on multiple datasets under various ratios of noisy labels and noise types outperforms other classifiers of learning with noisy labels (LNLs), including the state-of-the-art meta-data-based LNL classifier.

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
  • 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
  • Citations124

IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary

  • May 24, 2021
  • Xiaoyu Cao +2
  • Research Article
  • Citations16

Skin Lesion Segmentation in Dermoscopic Images with Noisy Data.

  • Apr 05, 2023
  • Journal of digital imaging
  • Norsang Lama +4
  • Conference Article

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks

  • Jan 01, 2016
  • Mostafa Shahin +1
  • Conference Article
  • Citations3

An Effective Integrated Intrusion Detection Model Based on Deep Neural Network

  • Jun 01, 2021
  • Wei Wan +5
  • Research Article
  • Citations82

Growing random forest on deep convolutional neural networks for scene categorization

  • Oct 17, 2016
  • Expert Systems with Applications
  • Shuang Bai
  • 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
  • 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
  • Citations15

Learning from Multi-annotator Data

  • Feb 21, 2019
  • ACM Transactions on Information Systems
  • Xueying Zhan +3
  • 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
  • Conference Article
  • Citations2

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

  • Sep 01, 2019
  • Shehani N Ariyathilake +1
  • 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.