VisDA-2021 Competition: Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data

Dina Bashkirova, Dan Hendrycks, Donghyun Kim, Haojin Liao, Samarth Mishra, Chandramouli Rajagopalan, Kate Saenko, Kuniaki Saito, Burhan Ul Tayyab, Piotr Teterwak, Ben Usman

Abstract: Progress in machine learning is typically measured by training and testing a model on samples drawn from the same distribution, i.e. the same domain. This over-estimates future accuracy on out-of-d...