软件导刊2024，Vol.23Issue(1)：42-49,8.DOI:10.11907/rjdk.231109
基于多分类器差异的噪声矫正域适应学习
Noise Correction Domain Adaptation Learning Based on Classifiers Discrepancy
摘要
Abstract
Unsupervised domain adaption(UDA)aims to transfer knowledge from the related and label-rich source domain to the label-scarce target domain.Usually,domain adaptation methods assume that the source data is correctly labeled.However,the labels and features of source samples will be destroyed due to the actual noise environment.To solve the problem of noisy source domain,this paper proposed noise correction domain adaptation based on classifiers discrepancy(NCDA).First,this method made a more precise classification standard by the difference between multiple classifiers in the network,which can divide noisy source samples into feature noise samples,label noise samples,and clean samples.Second,different correction methods were applied on them.Then,the corrected samples were put back into the training procedure.Finally,this paper used the idea of stochastic classifiers to improve the network.Extensive experiments on Office-31,Office-Home and Bing-Caltech demonstrated the effectiveness and robustness of NCDA,whose accuracy is 0.2%～1.6%higher than the sub-optimal method.关键词
无监督域适应/噪声检测/噪声矫正/机器学习Key words
unsupervised domain adaptation/noise detection/noise correction/machine learning分类
信息技术与安全科学引用本文复制引用
郑潍雯,汪云云..基于多分类器差异的噪声矫正域适应学习[J].软件导刊,2024,23(1):42-49,8.基金项目
国家自然科学基金面上项目(61876091,61772284,62006126) （61876091,61772284,62006126）
