Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation

Yao, Yuan1; Zhang, Yu2; Li, Xutao1; Ye, Yunming1

2020

10.1016/j.patcog.2019.107165

PATTERN RECOGNITION   影响因子和分区

0031-3203

1873-5142

Heterogeneous domain adaptation (HDA) aims to leverage knowledge from a source domain for helping learn an accurate model in a heterogeneous target domain. HDA is exceedingly challenging since the feature spaces of domains are distinct. To tackle this issue, we propose a unified learning framework called Discriminative Distribution Alignment (DDA) for deriving a domain-invariant subspace. The proposed DDA can simultaneously match the discriminative directions of domains, align the distributions across domains, and enhance the separability of data during adaptation. To achieve this, DDA trains an adaptive classifier by both reducing the distribution divergence and enlarging distances between class centroids. Based on the proposed DDA framework, we further develop two methods, by embedding the cross-entropy loss and squared loss into this framework, respectively. We conduct experiments on the tasks of categorization across domains and modalities. Experimental results clearly demonstrate that the proposed DDA outperforms several state-of-the-art models.
© 2020 Elsevier Ltd

Heterogeneous domain adaptation Subspace learning Classifier adaptation Distribution alignment Discriminative embedding

EI ; SCI

英语

其他

[2018YFB0504900] ; Shenzhen Technology Development Program[]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000525824600002

Elsevier Ltd

20200308050637

Embeddings ; Knowledge management

Mechanical Devices:601.1 ; Computer Applications:723.5

ENGINEERING

EV Compendex

1.Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
2.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China

Yao, Yuan,Zhang, Yu,Li, Xutao,et al. Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation[J]. PATTERN RECOGNITION,2020,101.

Yao, Yuan,Zhang, Yu,Li, Xutao,&Ye, Yunming.(2020).Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation.PATTERN RECOGNITION,101.

Yao, Yuan,et al."Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation".PATTERN RECOGNITION 101(2020).