Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 31, Issue 8, Pages 3073-3086Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2019.2935384
Keywords
Feature extraction; Adaptation models; Neural networks; Transforms; Training; Task analysis; Gallium nitride; Adversarial neural networks; residual connections; transfer learning; unsupervised domain adaptation (DA)
Categories
Funding
- National Natural Science Foundation of China [61772369, 61773166, 61771144, 61871004]
- National Science Foundation of China [U18092006]
- Shanghai Municipal Science and Technology Committee of Shanghai Outstanding Academic Leaders Plan [19XD1434000]
- Projects of International Cooperation of Shanghai Municipal Science and Technology Committee [19490712800]
- Shanghai Science and Technology Committee [17411953100]
- National Key Research and Development Program [2018YFB1004701]
- Fundamental Research Funds for the Central Universities
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available