Partial Adversarial Domain Adaptation

ECCV, 2018.

Cited by: 67|Bibtex|Views15|Links
EI

Abstract:

Domain adversarial learning aligns the feature distributions across the source and target domains in a two-player minimax game. Existing domain adversarial networks generally assume identical label space across different domains. In the presence of big data, there is strong motivation of transferring deep models from existing big domains ...More

Code:

Data:

Your rating :
0

 

Tags
Comments