Skip to content

Minimal-Entropy Diversity Maximization for Unsupervised Domain Adaptation

Notifications You must be signed in to change notification settings

freeSubmission/MEDM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MEDM

Minimal-Entropy Diversity Maximization for Unsupervised Domain Adaptation

On the largest domain-adaptation dataset VisDA-2017, MEDM-Res50 achieves 79.6% and MEDM-Res101 achieves 82.4% both in the mean accuracy, which might be the top-1 performing UDA algorithm as best as I know until the declaration of this code.

About

Minimal-Entropy Diversity Maximization for Unsupervised Domain Adaptation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages