Reliable Label Correction is a Good Booster When Learning with Extremely
Noisy Labels

v1v2 (latest)

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

30 April 2022

Yang You

ArXiv (abs)PDF HTML

Papers citing "Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels"

5 / 5 papers shown

Title
Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation Xinyang Huang Chuang Zhu Bowen Zhang Shanghang Zhang 100 2 0 11 Nov 2024
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency Shuo Yang Zhaopan Xu Kai Wang Yang You Huanjin Yao Tongliang Liu Min Xu 146 41 0 22 Mar 2023
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors Jianfei Yang Xiangyu Peng Kaidi Wang Zheng Hua Zhu Jiashi Feng Lihua Xie Yang You 139 33 0 28 May 2022
Dataset Pruning: Reducing Training Data by Examining Generalization Influence Shuo Yang Zeke Xie Hanyu Peng Minjing Xu Mingming Sun P. Li DD 297 131 0 19 May 2022
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network Shuo Yang Erkun Yang Bo Han Yang Liu Min Xu Gang Niu Tongliang Liu NoLa BDL 131 46 0 27 May 2021