Improving deep label noise learning with dual active label correction

DOI10.1007/S10994-021-06081-9MaRDI QIDQ2673328zbMATH OpenOpenAlexFDO

Authors Shao-Yuan Li, Y. Shi, Sheng-Jun Huang, Songcan Chen

Publication date 9 June 2022

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-021-06081-9

zbMATH Keywords

active learningdeep neural networkslabel noisenoise model

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07)

Recommendations

• How to handle noisy labels for robust learning from uncertainty
• Corrigendum to: ``Classification with asymmetric label noise: consistency and maximal denoising
• Active learning in heteroscedastic noise
• Towards harnessing feature embedding for robust learning with noisy labels

Cites work

• A theory of learning with corrupted labels
• scientific article; zbMATH DE number 6982911 (Why is no real title available?)

Cited in

(2)

• Confident learning: estimating uncertainty in dataset labels
• How to handle noisy labels for robust learning from uncertainty

Describes a project that uses

Uses Software

• DivideMix
• MentorNet
• mlj21DALC
• MixMatch
• MNIST
• CIFAR
• SGDR
• mixup

This page was built for publication: Improving deep label noise learning with dual active label correction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2673328)