Noise-free prototype guided representation calibration under label noise
Authors:
- Huiting YuanHYHuiting Yuan
- Tingjin LuoTLTingjin Luo
- Xinghao WuXWXinghao Wu
- Jie JiangJJJie Jiang
- 22 August 2025
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 329
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62376281)
- National Natural Science Foundation of China (62136005)
This publication has 9 references indexed in Scilit:
- Tackling Noisy Labels With Network Parameter Additive DecompositionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Regularly Truncated M-Estimators for Learning With Noisy LabelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Prototype-Guided Feature Learning for Unsupervised Domain AdaptationPattern Recognition, 2022
- Prototype-based classifier learning for long-tailed visual recognitionScience China Information Sciences, 2022
- Learning From Noisy Labels With Deep Neural Networks: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2022
- Understanding deep learning (still) requires rethinking generalizationCommunications of the ACM, 2021
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep learningNature, 2015