Noisy Label Learning

Noisy label learning tackles the challenge of training machine learning models on datasets containing inaccurate labels, a common problem in real-world applications. Current research focuses on developing robust algorithms that can identify and mitigate the effects of noisy labels, employing techniques such as sample selection, label correction, and the integration of semi-supervised and contrastive learning methods within various model architectures (e.g., mixture models, co-teaching networks). These advancements are crucial for improving the reliability and generalizability of machine learning models across diverse domains, particularly where obtaining perfectly labeled data is impractical or expensive. The resulting improvements in model accuracy and robustness have significant implications for various fields, including healthcare, computer vision, and natural language processing.

Papers

November 3, 2024

ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels
Filipe R. Cordeiro, Gustavo Carneiro
Noisy Label Nearest Neighbor Robust Learning Noisy Label Learning Sample Selection Eigen Portfolio Noisy Label Sample

October 31, 2024

CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning
Yeachan Kim, Junho Kim, SangKeun Lee
Native Robustness Noisy Label Parameter Efficient Fine Tuning Noisy Label Learning

July 10, 2024

Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction
Po-Hsuan Huang, Chia-Ching Lin, Chih-Fan Hsu, Ming-Ching Chang, Wei-Chao Chen
LeArning Abstract Model Hallucination Semi Supervised Training Noisy Label Learning Instance Dependent Noise Instance Dependent Label Noise

May 8, 2024

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning
Rui Zhao, Bin Shi, Jianfei Ruan, Tianze Pan, Bo Dong
Noisy Label Posterior Approximation Noisy Label Learning Noisy Class

May 2, 2024

Potential Energy based Mixture Model for Noisy Label Learning
Zijia Wang, Wenbin Yang, Zhisong Liu, Zhen Jia
Deep Neural Network Noisy Label Label Noise Mixture Model Noisy Label Learning

April 16, 2024

Robust Noisy Label Learning via Two-Stream Sample Distillation
Sihan Bai, Sanping Zhou, Zheng Qin, Le Wang, Nanning Zheng
Noisy Label Noisy Label Learning Pseudo Sample

April 2, 2024

Pairwise Similarity Distribution Clustering for Noisy Label Learning
Sihan Bai
Noisy Label Pairwise Similarity Noisy Label Learning Label Confidence Similarity Distribution

March 5, 2024

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
HeeSun Bae, Seungjae Shin, Byeonghu Na, Il-Chul Moon
Noisy Label Noisy Label Learning Weighted Sampling Transition Matrix Noise Transition Matrix

January 25, 2024

Learning under Label Noise through Few-Shot Human-in-the-Loop Refinement
Aaqib Saeed, Dimitris Spathis, Jungwoo Oh, Edward Choi, Ali Etemad
LeArning Abstract Noisy Label Label Noise Wearable Sensor Data Noisy Label Learning Wearable Technology

January 16, 2024

Robust Tiny Object Detection in Aerial Images amidst Label Noise
Haoran Zhu, Chang Xu, Wen Yang, Ruixiang Zhang, Yan Zhang, Gui-Song Xia
Object Detector Robust Version Label Noise Aerial Image Noisy Label Learning Tiny Object Detection

December 15, 2023

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning
Mengmeng Sheng, Zeren Sun, Zhenhuang Cai, Tao Chen, Yichao Zhou, Yazhou Yao
Partial Label Learning Noisy Label Learning Seamless Integration Complementary Label Negative Learning Label Disambiguation

September 27, 2023

Learning with Noisy Labels for Human Fall Events Classification: Joint Cooperative Training with Trinity Networks
Leiyu Xie, Yang Sun, Syed Mohsen Naqvi
LeArning Abstract Noisy Label Fall Detection Data Labeling Noisy Label Learning Joint Training Fall Event Classification

August 2, 2023

Partial Label Supervision for Agnostic Generative Noisy Label Learning
Fengbei Liu, Chong Wang, Yuanhong Chen, Yuyuan Liu, Gustavo Carneiro
Generative Model Noisy Label Learning Label Supervision

July 29, 2023

A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification
Mingcai Chen, Yu Zhao, Zhonghuang Wang, Bing He, Jianhua Yao
New Formulation Noisy Label Learning Immune Repertoire

July 28, 2023

Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
Renyu Zhu, Haoyu Liu, Runze Wu, Minmin Lin, Tangjie Lv, Changjie Fan, Haobo Wang
Semi Supervised Learning Noisy Label Label Noise Noisy Label Learning Noisy Observation

June 20, 2023

FedNoisy: Federated Noisy Label Learning Benchmark
Siqi Liang, Jintao Huang, Junyuan Hong, Dun Zeng, Jiayu Zhou, Zenglin Xu
Noisy Label Noisy Label Learning

May 9, 2023

FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity
Nannan Wu, Li Yu, Xuefeng Jiang, Kwang-Ting Cheng, Zengqiang Yan
Label Noise Class Imbalance Noisy Label Learning Robust Federated Learning

April 6, 2023

Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients
Chenrui Wu, Zexi Li, Fangxin Wang, Chao Wu
Label Noise Industrial Disturbing Noise Class Imbalance Heterogeneous Client Noisy Label Learning Safe Learning Mixup Training

January 12, 2023

1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification Track
Yilu Guo, Xingyue Shi, Weijie Chen, Shicai Yang, Di Xie, Shiliang Pu, Yueting Zhuang
Distribution Generalization Place Solution Noisy Label Learning Ood Cv

January 4, 2023

Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach
Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro
Noisy Label Label Noise Novel Identifiability Test Noisy Label Learning Multinomial Mixture

Noisy Label Learning

Papers

ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels

CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning

Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction

Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning

Potential Energy based Mixture Model for Noisy Label Learning

Robust Noisy Label Learning via Two-Stream Sample Distillation

Pairwise Similarity Distribution Clustering for Noisy Label Learning

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

Learning under Label Noise through Few-Shot Human-in-the-Loop Refinement

Robust Tiny Object Detection in Aerial Images amidst Label Noise

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning

Learning with Noisy Labels for Human Fall Events Classification: Joint Cooperative Training with Trinity Networks

Partial Label Supervision for Agnostic Generative Noisy Label Learning

A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification

Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective

FedNoisy: Federated Noisy Label Learning Benchmark

FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity

Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients

1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification Track

Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach