Quantcast
Channel: College of Arts and Sciences
Viewing all articles
Browse latest Browse all 1561

Surprisingly simple semi-supervised domain adaptation with pretraining and consistency

$
0
0
Surprisingly simple semi-supervised domain adaptation with pretraining and consistency Mishra, Samarth; Saenko, Kate; Saligrama, Venkatesh Visual domain adaptation involves learning to classify images from a target visual domain using labels available in a different source domain. A range of prior work uses adversarial domain alignment to try and learn a domain invariant feature space, where a good source classifier can perform well on target data. This however, can lead to errors where class A features in the target domain get aligned to class B features in source. We show that in the presence of a few target labels, simple techniques like selfsupervision (via rotation prediction) and consistency regularization can be effective without any adversarial alignment to learn a good target classifier. Our Pretraining and Consistency (PAC) approach, can achieve state of the art accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets. Notably, it outperforms all recent approaches by 3-5% on the large and challenging DomainNet benchmark, showing the strength of these simple techniques in fixing errors made by adversarial alignment

Viewing all articles
Browse latest Browse all 1561

Trending Articles