| Presentation | 2022-02-21 Regularizing Generative Adversarial Networks with Internal Representation of Generators Yusuke Hara, Toshihiko Yamasaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In training generative adversarial networks, maintaining the criteria of the discriminator stably is crucial to training speed and quality. To address this issue, we propose a new regularization term which makes the discriminator learn to estimate information deriving from the internal representation of the generator. Moreover, we propose a new consistency regularization (CR) on the estimation. While existing CR methods using the real-or-fake output allow the generator to learn the augmented distribution, our CR suppresses this problem. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Generative Adversarial Networks / Image Generation / Deep Learning |
| Paper # | ITS2021-29,IE2021-38 |
| Date of Issue | 2022-02-14 (ITS, IE) |
| Conference Information | |
| Committee | IE / ITS / ITE-AIT / ITE-ME / ITE-MMS |
|---|---|
| Conference Date | 2022/2/21(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Image Processing, etc. |
| Chair | Kazuya Kodama(NII) / Masahiro Fujii(Utsunomiya Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.) / Hiroyuki Arai(Nippon Inst. of Tech.) / Kenji Machida(NHK) |
| Vice Chair | Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Kohei Ohno(Meiji Univ.) / Naohisa Hashimoto(AIST) / / Shogo Muramatsu(Niigata Univ.) |
| Secretary | Hiroyuki Bandoh(KDDI Research) / Toshihiko Yamazaki(Nagoya Inst. of Tech.) / Kohei Ohno(Akita Prefectural Univ.) / Naohisa Hashimoto(NIT, Tsuruoka College) / / Shogo Muramatsu(NHK) / (Hokkaido Univ.) |
| Assistant | Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Msataka Imao(Mitsubishi Electric) / Kenshi Saho(Toyama Prefectural Univ.) / Keiji Jimi(Gunma Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Artistic Image Technology / Technical Group on Media Engineering / Technical Group on Multi-media Storage |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Regularizing Generative Adversarial Networks with Internal Representation of Generators |
| Sub Title (in English) | |
| Keyword(1) | Generative Adversarial Networks |
| Keyword(2) | Image Generation |
| Keyword(3) | Deep Learning |
| 1st Author's Name | Yusuke Hara |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Toshihiko Yamasaki |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2022-02-21 |
| Paper # | ITS2021-29,IE2021-38 |
| Volume (vol) | vol.121 |
| Number (no) | ITS-373,IE-374 |
| Page | pp.pp.25-30(ITS), pp.25-30(IE), |
| #Pages | 6 |
| Date of Issue | 2022-02-14 (ITS, IE) |