Fully Test-time Adaptation by Entropy Minimization

Dequan Wang
Dequan Wang
Shaoteng Liu
Shaoteng Liu
Bruno Olshausen
Bruno Olshausen

international conference on learning representations, 2020.

Cited by: 0|Bibtex|Views115
Other Links: arxiv.org|academic.microsoft.com

Abstract:

Faced with new and different data during testing, a model must adapt itself. We consider the setting of fully test-time adaptation, in which a supervised model confronts unlabeled test data from a different distribution, without the help of its labeled training data. We propose an entropy minimization approach for adaptation: we take th...More

Code:

Data:

Your rating :
0

 

Tags
Comments