Noisy Label

Noisy label learning (NLL) tackles the challenge of training machine learning models on datasets containing inaccurate labels, a common problem in large-scale data collection. Current research focuses on developing robust algorithms and model architectures, such as vision transformers and graph neural networks, that can effectively mitigate the negative impact of noisy labels, often employing techniques like sample selection, loss function modification, and self-supervised learning. These advancements are crucial for improving the reliability and generalizability of machine learning models across various applications, from image classification and natural language processing to medical image analysis and remote sensing. The ultimate goal is to build more robust and reliable AI systems that can handle the imperfections inherent in real-world data.

Papers

February 14, 2023

Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cai Rong Zhao
LeArning Abstract Noisy Label Deep Feature Real World Noisy Datasets Adversarial Mask Self Supervised Signal

February 6, 2023

APAM: Adaptive Pre-training and Adaptive Meta Learning in Language Model for Noisy Labels and Long-tailed Learning
Sunyi Chi, Bo Dong, Yiming Xu, Zhenyu Shi, Zheng Du
Language Model Contrastive Learning Loss Function Meta Learning Adaptive Importance Noisy Label Cross Entropy Loss Self Supervised Pre Training Long Tailed Learning Weighting Function

February 1, 2023

Free Lunch for Domain Adversarial Training: Environment Label Smoothing
YiFan Zhang, Xue Wang, Jian Liang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Noisy Label Label Noise Domain Adversarial Free Lunch Domain Discriminator

January 31, 2023

When Source-Free Domain Adaptation Meets Learning with Noisy Labels
Li Yi, Gezheng Xu, Pengcheng Xu, Jiaqi Li, Ruizhi Pu, Charles Ling, A. Ian McLeod, Boyu Wang
LeArning Abstract Domain Shift Noisy Label Label Noise Source Free Domain Adaptation

January 25, 2023

Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection
Tongzhi Niu, Bin Li, Kai Li, Yufeng Lin, Yuwei Li, Weifeng Li, Zhenrong Wang
Noisy Label False Positive Surface Defect Detection Rough Set Trustworthy Deep Learning Surface Defect

January 9, 2023

A Robust Multilabel Method Integrating Rule-based Transparent Model, Soft Label Correlation Learning and Label Noise Resistance
Qiongdan Lou, Zhaohong Deng, Kup-Sze Choi, Shitong Wang
Noisy Label Soft Label Label Correlation Multilabel Classification

January 4, 2023

January 2, 2023

Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels
Yikai Wang, Yanwei Fu, Xinwei Sun
LeArning Abstract Noisy Label Noisy Data Real World Noisy Datasets Clean Sample

January 1, 2023

Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learning
Fengbei Liu, Yuanhong Chen, Chong Wang, Yu Tain, Gustavo Carneiro
Noisy Label Multi Label Noisy Label Learning Local Consensus Noisy Label Sample Co Teaching

December 28, 2022

Learning to Detect Noisy Labels Using Model-Based Features
Zhihao Wang, Zongyu Lin, Peiqi Liu, Guidong ZHeng, Junjie Wen, Xianxin Chen, Yujun Chen, Zhilin Yang
LeArning Abstract Meta Learning Noisy Label Label Noise Label Corruption

December 27, 2022

Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos
Zixiao Wang, Junwu Weng, Chun Yuan, Jue Wang
Contrastive Learning New Framework Noisy Label Label Noise Differentiable Channel

December 21, 2022

Class Prototype-based Cleaner for Label Noise Learning
Jingjia Huang, Yuanqi Chen, Jiashi Feng, Xinglong Wu
Semi Supervised Noisy Label Label Noise Noisy Label Learning Category Prototype

December 19, 2022

Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
Qingrui Jia, Xuhong Li, Lei Yu, Jiang Bian, Penghao Zhao, Shupeng Li, Haoyi Xiong, Dejing Dou
LeArning Abstract Noisy Label Label Noise Training Dynamic Labeled Sample

December 14, 2022

Improving group robustness under noisy labels using predictive uncertainty
Dongpin Oh, Dae Lee, Jeunghyun Byun, Bonggun Shin
Noisy Label Empirical Risk Minimization Predictive Uncertainty Group Robustness Worst Group Accuracy Uncertain Sample Spurious Cue

December 8, 2022

December 7, 2022

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
Huaxi Huang, Hui Kang, Sheng Liu, Olivier Salvado, Thierry Rakotoarivelo, Dadong Wang, Tongliang Liu
LeArning Abstract Convolutional Neural Network Noisy Label Label Noise Disentanglement Method Stop or Go Decision Phase Spectrum

December 3, 2022