Heterogeneous domain adaptation via soft transfer network

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

10.1145/3343031.3350955

2019-10-15

MM 2019 - Proceedings of the 27th ACM International Conference on Multimedia

1578-1586

Nice, France

1515 BROADWAY, NEW YORK, NY 10036-9998 USA

Association for Computing Machinery, Inc

Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for addressing the HDA problem. The proposed STN not only aligns the discriminative directions of domains but also matches both the marginal and conditional distributions across domains. To circumvent negative transfer, STN aligns the conditional distributions by using the soft-label strategy of unlabeled target data, which prevents the hard assignment of each unlabeled target data to only one category that may be incorrect. Further, STN introduces an adaptive coefficient to gradually increase the importance of the soft-labels since they will become more and more accurate as the number of iterations increases. We perform experiments on the transfer tasks of image-to-image, text-to-image, and text-to-text. Experimental results testify that the STN significantly outperforms several state-of-the-art approaches.

Adaptive coefficient Heterogeneous domain adaptation Soft-label Subspace learning

其他

英语

EI ; CPCI-S

[2018YFB0504905] ; Shenzhen Technology Development Program[JCYJ20170811160212033] ; National Natural Science Foundation of China[61673202]

Computer Science

Computer Science, Interdisciplinary Applications ; Computer Science, Theory & Methods

WOS:000509743400196

20194607685191

2-s2.0-85074870905

Scopus

1.School 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. Heterogeneous domain adaptation via soft transfer network[C]. 1515 BROADWAY, NEW YORK, NY 10036-9998 USA:Association for Computing Machinery, Inc,2019:1578-1586.