A review on label cleaning techniques for learning with noisy labels

Classification models categorize objects into given classes, guided by training samples with input features and labels. In practice, however, labels can be corrupted by human error or mistakes, known as label noise, which degrades classification accuracy. To address this issue, recently, various wor...

Full description

Saved in:
Bibliographic Details
Main Authors: Jongmin Shin, Jonghyeon Won, Hyun-Suk Lee, Jang-Won Lee
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:ICT Express
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405959524001103
Tags: Add Tag
No Tags, Be the first to tag this record!