Fisher deep domain adaptation

Zhang，Yinghua1; Zhang，Yu2; Wei，Ying3; Bai，Kun3; Song，Yangqiu1; Yang，Qiang1,4

10.1137/1.9781611976236.53

2020

Proceedings of the 2020 SIAM International Conference on Data Mining, SDM 2020

469-477

Deep domain adaptation models learn a neural network in an unlabeled target domain by leveraging the knowledge from a labeled source domain. This can be achieved by learning a domain-invariant feature space. Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance. To fill the gap, a Fisher loss is proposed to learn discriminative representations which are within-class compact and between-class separable. Experimental results on two benchmark datasets show that the Fisher loss is a general and effective loss for deep domain adaptation. Noticeable improvements are brought when it is used together with widely adopted transfer criteria, including MMD, CORAL and domain adversarial loss. For example, an absolute improvement of 6.67% in terms of the mean accuracy is attained when the Fisher loss is used together with the domain adversarial loss on the Office-Home dataset.

其他

英语

EI

20203309034654

Space division multiple access ; Data mining

Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Information Retrieval and Use:903.3

2-s2.0-85089190175

Scopus

1.Department of Computer Science and Engineering,Hong Kong University of Science and Technology,Hong Kong
2.Department of Computer Science and Engineering,Southern University of Science and Technology,
3.Tencent,
4.WeBank,

Zhang，Yinghua,Zhang，Yu,Wei，Ying,et al. Fisher deep domain adaptation[C],2020:469-477.