Unsupervised domain adaptation with adversarial residual transform networks

Document Type

Article

Publication Date

8-1-2020

Abstract

Domain adaptation (DA) is widely used in learning problems lacking labels. Recent studies show that deep adversarial DA models can make markable improvements in performance, which include symmetric and asymmetric architectures. However, the former has poor generalization ability, whereas the latter is very hard to train. In this article, we propose a novel adversarial DA method named adversarial residual transform networks (ARTNs) to improve the generalization ability, which directly transforms the source features into the space of target features. In this model, residual connections are used to share features and adversarial loss is reconstructed, thus making the model more generalized and easier to train. Moreover, a special regularization term is added to the loss function to alleviate a vanishing gradient problem, which enables its training process stable. A series of experiments based on Amazon review data set, digits data sets, and Office-31 image data sets are conducted to show that the proposed ARTN can be comparable with the methods of the state of the art.

Identifier

85089124828 (Scopus)

Publication Title

IEEE Transactions on Neural Networks and Learning Systems

External Full Text Location

https://doi.org/10.1109/TNNLS.2019.2935384

e-ISSN

21622388

ISSN

2162237X

PubMed ID

31514161

First Page

3073

Last Page

3086

Issue

8

Volume

31

Grant

19XD1434000

Fund Ref

National Natural Science Foundation of China

This document is currently not available here.

Share

COinS