Research Of Source-Free Unsupervised Domain Adaptation Algorithm

Unsupervised domain adaptation(UDA)is used to extend the model working on well-annotated source data to unlabeled target data.However,in practice,due to privacy and storage issues,we can only obtain the well-trained source model.This paper focus on this scenario named source-free domain adaptation(SFDA).At present,nearest neighbors-based SFDA methods assume that the target features extracted by the source model can form clear clusters,and align samples with their neighbors.However,due to the domain discrepancy,adjacent features may belong to different categories.This paper propose consistency regularization-based mutual alignment(CRMA)to address this problem.Firstly,CRMA randomly augment each target sample.Due to the domain discrepancy,It may lead to negative transfer if aligning them directly.Therefore,secondly,CRMA leverage the information maximization loss to all target and augmented samples,improving the performance of mutual alignment.Finally,CRMA mutually align original samples and augmented samples.It improves the ability of the model and increases the variety of samples to alleviate the phenomenon that incorrectly aligning samples when aligning with neighbors.CRMA achieves state-of-the-art performance on 3 popular cross-domain benchmarks.Compared with the original method,CRMA has improvements of 0.4% up to89.4%,1.9% up to 72.2%,and 1.9% up to 85.9% on 3 datasets respectively.At the last,this verify the effectiveness of each part of CRMA through ablation experiments and use a series of experiments to analyze CRMA in detail.