Contrastive Test-Time Adaptation

Test-time adaptation is a special setting of unsupervised domain adaptation where a trained model on the source domain has to adapt to the target domain without accessing source data. We propose a novel way to leverage self-supervised contrastive learning to facilitate target feature learning, along...

Full description

Bibliographic Details

Main Authors:	Chen, Dian, Wang, Dequan, Darrell, Trevor, Ebrahimi, Sayna
Format:	Conference Proceeding
Language:	English
Subjects:	Adaptation models Benchmark testing Calibration Data models Machine learning Efficient learning and inferences Representation learning Self-& semi-& meta- & unsupervised learning Memory management Pattern recognition Representation learning
Online Access:	Request full text
Tags:	Add Tag No Tags, Be the first to tag this record!