Unsupervised Domain Adaptation Based on Entropy Filtering and Class Centroid Optimization
As one of the emerging research directions in the field of machine learning,unsupervised domain adaptation mainly uses source domain supervision information to assist the learning of unlabeled target domains.Recently,many unsupervised domain adaptation methods have been proposed,but there are still some deficiencies in relation mining.Specifically,existing methods usually adopt a consistent processing strategy for target domain samples,while ignoring the discrepancy in target domain samples in relation mining.Therefore,this paper proposes a novel method called entropy filtering and class centroid optimization(EFCO).The proposed method utilizes a generative adversarial network architecture to label target domain samples.With the obtained pseudo-labels,the sample entropy value is calculated and compared with a predefined threshold to further categorize target domain samples.Simple samples are assigned pseudo-labels,while difficult samples are classified using the idea of contrastive learning.By combining source domain data and simple samples,a more robust classifier is learned to classify difficult samples,and class cen-troids of the source and target domains are obtained.Inter-domain and intra-domain discrepancies are minimized by optimizing in-ter-domain contrastive alignment and instance contrastive alignment.Finally,it is compared with several advanced domain adapta-tion methods on three standard data sets,and the results indicate that the performance of the proposed method outperforms the comparison methods.
Transfer learningUnsupervised domain adaptationAdversarial learningContrastive learningClass centroid optimi-zation
NETL
NSTL
万方数据
