| Presentation | 2020-12-23 Analysis of human subjective evaluation using deep neural networks Yoshiyuki Sato, Kazuya Matsubara, Yuji Wada, Satoshi Shioiri, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this research, we constructed an deep learning model to learn and predict several different subjective judgments by human (desire to eat, whether it is made for young people, etc.) for food images. We show that our deep learning model successfully predict the different human subjective judgements. Furthermore, we analyze the parts of images which contribute to the judgment of the deep learning model using a visual explanation technique. We show that the model uses relative narrow regions of the images when it judges higher rating for higher-rated images by human raters. On the other hand, the model uses relatively broad regions when it judges lower rating for lower-rated images by humans raters. Our future work is to compare the visual explanation of the model to the factor that affects the subjective ratings by humans. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning model / Subjective rating prediction / Food image / Visual explanation |
| Paper # | HIP2020-68 |
| Date of Issue | 2020-12-15 (HIP) |
| Conference Information | |
| Committee | HIP |
|---|---|
| Conference Date | 2020/12/22(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shuichi Sakamoto(Tohoku Univ.) |
| Vice Chair | Yuji Wada(Ritsumeikan Univ.) / Sachiko Kiyokawa(Nagoya Univ.) |
| Secretary | Yuji Wada(NICT) / Sachiko Kiyokawa(NTT) |
| Assistant | Hidetoshi Kanaya(Ritsumeikan Univ.) / Yuki Yamada(Kyushu Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Human Information Processing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Analysis of human subjective evaluation using deep neural networks |
| Sub Title (in English) | |
| Keyword(1) | Deep learning model |
| Keyword(2) | Subjective rating prediction |
| Keyword(3) | Food image |
| Keyword(4) | Visual explanation |
| 1st Author's Name | Yoshiyuki Sato |
| 1st Author's Affiliation | Tohoku University(Tohoku Univ.) |
| 2nd Author's Name | Kazuya Matsubara |
| 2nd Author's Affiliation | Ritsmeikan University(Ritsmeikan Univ.) |
| 3rd Author's Name | Yuji Wada |
| 3rd Author's Affiliation | Ritsmeikan University(Ritsmeikan Univ.) |
| 4th Author's Name | Satoshi Shioiri |
| 4th Author's Affiliation | Tohoku University(Tohoku Univ.) |
| Date | 2020-12-23 |
| Paper # | HIP2020-68 |
| Volume (vol) | vol.120 |
| Number (no) | HIP-306 |
| Page | pp.pp.77-80(HIP), |
| #Pages | 4 |
| Date of Issue | 2020-12-15 (HIP) |