Abstract
Generative adversarial network (GAN) is an implicit generative model known for its ability to generate sharp images. However, it is poor at generating diverse data, which refers to the mode collapse problem. It turns out that GAN is prone to emphasizing the quality of samples but ignoring their diversity. When mode collapse happens, the support of the generated data distribution is not aligned with that of the real data distribution. We thus propose Support Regularized-GAN (SR-GAN) to address such a mode collapse issue by matching their support. Our experiments on synthetic and real-world datasets show that our regularization can mitigate the mode collapse and also improve the data quality.
Original language | English |
---|---|
Title of host publication | Neural Information Processing : 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12–15, 2019, Proceedings, Part IV |
Editors | Tom GEDEON, Kok Wai WONG, Minho LEE |
Publisher | Springer |
Pages | 40-48 |
Number of pages | 9 |
ISBN (Electronic) | 9783030368081 |
ISBN (Print) | 9783030368074 |
DOIs | |
Publication status | Published - 2019 |
Externally published | Yes |
Event | 26th International Conference on Neural Information Processing - Sydney, Australia Duration: 12 Dec 2019 → 15 Dec 2019 |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Publisher | Springer |
Volume | 1142 |
ISSN (Print) | 1865-0929 |
ISSN (Electronic) | 1865-0937 |
Conference
Conference | 26th International Conference on Neural Information Processing |
---|---|
Abbreviated title | ICONIP 2019 |
Country/Territory | Australia |
City | Sydney |
Period | 12/12/19 → 15/12/19 |
Bibliographical note
Publisher Copyright:© Springer Nature Switzerland AG 2019.
Funding
This work was supported by the National Key R&D Program of China (Grant No. 2017YFC0804003), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No. 2017ZT07X386), Shenzhen Peacock Plan (Grant No. KQTD2016112514355531), the Program for University Key Laboratory of Guangdong Province (Grant No. 2017KSYS008), and Australian Research Council (Grant No. LP150100671 and No. DP180100106).
Keywords
- GANs
- Mode collapse
- Support matching