Ajou University repository

Improving Generative Adversarial Networks with Adaptive Control Learning
Citations

SCOPUS

0

Citation Export

Publication Year
2018-07-02
Journal
VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing
Keyword
Adaptive algorithmGenerative adversarial networksImage synthesis
Mesh Keyword
Adaptive ControlAdversarial networksData collectionHyper-parameterImage synthesisRealistic imagesStatic approachVisual objects
All Science Classification Codes (ASJC)
Computer Networks and CommunicationsSignal Processing
Abstract
Generative adversarial networks (GANs) are well known both for being unstable to train and for the problem of mode collapse, particularly when trained on data collections containing a diverse set of visual objects. This study introduces an adaptive hyper-parameter learning procedure for GANs as an alternative to the existing static approach. The proposed procedure is designed to mitigate the impact of instability and saturation in the original by dynamically adjusting the ratio of the training steps of both the generator and discriminator. To accomplish this, we track and analyze stable training curves of relatively narrow datasets and use them as the target fitting lines when training more diverse data collections. Experimental results show that the proposed model improves the stability and generates more realistic images.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36321
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85065424488&origin=inward
DOI
https://doi.org/10.1109/vcip.2018.8698669
Journal URL
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8694905
Type
Conference
Funding
This work was supported in part by the MSIP (Ministry of Science and ICT) under ICT R&D program (2017-0-01672) supervised by the IITP (Institute for Information & communications Technology Promotion), in part by the National Natural Science Foundation of China (NSFC) under Grant 61806142.
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Sohn, Kyung-Ah Image
Sohn, Kyung-Ah손경아
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.