Presentation | 2022-02-21 Towards Universal Deep Image Compression Koki Tsubota, Hiroaki Akutsu, Kiyoharu Aizawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we investigate deep image compression towards universal usage. In image compression, it is desirable to be able to compress not only natural images but also images in a wide range of domains such as processed photographs, line drawings, and illustrations. However, deep image compression has been generally studied only for natural images and little has been studied for non-natural images. In this study, we first validate the existing deep image compression models using a dataset consisting of multiple domains. Then, we train a compression model on multiple domains and examine the performance on the training domains and unseen domains during training. This method is a baseline method for domain generalization and multi-domain learning. In experiments, we show that deep image compression methods trained on natural images achieve lower performance than traditional methods, especially at higher rates. We also show that while the average performance across multiple domains is higher when training on multiple domains than when training on a single domain, the best performance in each domain is achieved when training on only the evaluation domain. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | image compression / deep neural networks / domain generalization / multi-domain learning |
Paper # | ITS2021-31,IE2021-40 |
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) | Towards Universal Deep Image Compression |
Sub Title (in English) | |
Keyword(1) | image compression |
Keyword(2) | deep neural networks |
Keyword(3) | domain generalization |
Keyword(4) | multi-domain learning |
1st Author's Name | Koki Tsubota |
1st Author's Affiliation | The University of Tokyo(UTokyo) |
2nd Author's Name | Hiroaki Akutsu |
2nd Author's Affiliation | Hitachi, Ltd.(Hitachi) |
3rd Author's Name | Kiyoharu Aizawa |
3rd Author's Affiliation | The University of Tokyo(UTokyo) |
Date | 2022-02-21 |
Paper # | ITS2021-31,IE2021-40 |
Volume (vol) | vol.121 |
Number (no) | ITS-373,IE-374 |
Page | pp.pp.37-42(ITS), pp.37-42(IE), |
#Pages | 6 |
Date of Issue | 2022-02-14 (ITS, IE) |