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
Recommended Citation
Cai, Guanyu; Wang, Yuqin; He, Lianghua; and Zhou, Mengchu, "Unsupervised domain adaptation with adversarial residual transform networks" (2020). Faculty Publications. 5109.
https://digitalcommons.njit.edu/fac_pubs/5109
