郑州大学学报（理学版）2026，Vol.58Issue(1)：10-18,9.DOI:10.13705/j.issn.1671-6841.2024122
不确定性感知的标签噪声矫正算法
Uncertainty-aware Label Noise Correction Algorithm
摘要
Abstract
Label noise introduced issues of uncertainty into the training process of learning algorithms by reducing confidence in the prediction of true classes.To mitigate the impact of label noise,an uncertain-ty-aware label noise correction(ULC)algorithm for robust classification was proposed.Firstly,based on evidence theory and subjective logic theory,uncertainty was estimated from multiple perspectives and the label information of the sample.Secondly,the dataset was finely divided into three subsets.The noise la-bels within these subsets were then corrected using joint prediction.Finally,to optimize the training ob-jectives,each subset was processed using different regularization strategies.Comparative experiments were conducted on four simulated label noise datasets and two containing real label noise.On CIFAR-10 and CIFAR-100 with 40%pairflip-type label noise,the classification accuracy of ULC was increased by 10.58 percentage points and 15.84 percentage points compared to DivideMix,and the corrected label ac-curacy reached 95.48%and 81.32%,respectively.The simulation results showed that the proposed algo-rithm accurately estimated uncertainty,finely improved the accuracy of corrected labels,and enhanced model generalization performance.关键词
深度学习/标签噪声/不确定性估计/样本选择/标签矫正Key words
deep learning/label noise/uncertainty estimation/sample selection/label correction分类
信息技术与安全科学引用本文复制引用
李英双,贾文玉,杨莉,曾旺官,董永峰..不确定性感知的标签噪声矫正算法[J].郑州大学学报（理学版）,2026,58(1):10-18,9.基金项目
国家自然科学基金项目(62306103,62376194) （62306103,62376194）
河北省高等学校自然科学研究项目(QN2023262) （QN2023262）
河北省高等教育教学改革研究与实践项目(2022GJJG039) （2022GJJG039）
