Next Article in Journal
Designing Internet of Tangible Things for Children with Hearing Impairment
Next Article in Special Issue
Cyber Security Tool Kit (CyberSecTK): A Python Library for Machine Learning and Cyber Security
Previous Article in Journal
Delphi Method Supported by Forecasting Software
Previous Article in Special Issue
Kernel-Based Ensemble Learning in Python
Article

Spectral Normalization for Domain Adaptation

by * and
Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education (Northeast Electric Power University), Jilin 132012, China
*
Author to whom correspondence should be addressed.
Information 2020, 11(2), 68; https://doi.org/10.3390/info11020068
Received: 4 December 2019 / Revised: 1 January 2020 / Accepted: 20 January 2020 / Published: 27 January 2020
(This article belongs to the Special Issue Machine Learning with Python)
The transfer learning method is used to extend our existing model to more difficult scenarios, thereby accelerating the training process and improving learning performance. The conditional adversarial domain adaptation method proposed in 2018 is a particular type of transfer learning. It uses the domain discriminator to identify which images the extracted features belong to. The features are obtained from the feature extraction network. The stability of the domain discriminator directly affects the classification accuracy. Here, we propose a new algorithm to improve the predictive accuracy. First, we introduce the Lipschitz constraint condition into domain adaptation. If the constraint condition can be satisfied, the method will be stable. Second, we analyze how to make the gradient satisfy the condition, thereby deducing the modified gradient via the spectrum regularization method. The modified gradient is then used to update the parameter matrix. The proposed method is compared to the ResNet-50, deep adaptation network, domain adversarial neural network, joint adaptation network, and conditional domain adversarial network methods using the datasets that are found in Office-31, ImageCLEF-DA, and Office-Home. The simulations demonstrate that the proposed method has a better performance than other methods with respect to accuracy. View Full-Text
Keywords: deep learning; transfer learning; domain adaptation; adversarial network deep learning; transfer learning; domain adaptation; adversarial network
Show Figures

Figure 1

MDPI and ACS Style

Zhao, L.; Liu, Y. Spectral Normalization for Domain Adaptation. Information 2020, 11, 68. https://doi.org/10.3390/info11020068

AMA Style

Zhao L, Liu Y. Spectral Normalization for Domain Adaptation. Information. 2020; 11(2):68. https://doi.org/10.3390/info11020068

Chicago/Turabian Style

Zhao, Liquan; Liu, Yan. 2020. "Spectral Normalization for Domain Adaptation" Information 11, no. 2: 68. https://doi.org/10.3390/info11020068

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop