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

This paper addresses the performance degradation of deep neural networks caused by learning with noisy labels. Recent research on this topic has exploited the memorization effect: networks fit data with clean labels during the early stages of learning and eventually memorize data with noisy labels....

Full description

Bibliographic Details
Main Authors: Ryota Higashimoto, Soh Yoshida, Mitsuji Muneyasu
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/3/1208