Multi-source Distilling Domain Adaptation

Guangzhi Wang
Guangzhi Wang
Yang Gu
Yang Gu
Yaxian Li
Yaxian Li
Zhichao Song
Zhichao Song
Runbo Hu
Runbo Hu
Hua Chai
Hua Chai

AAAI, pp. 12975-12983, 2020.

Cited by: 20|Views110
EI

Abstract:

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution. However, in practice, labeled data...More

Code:

Data:

Your rating :
0

 

Tags
Comments