| Presentation | 2021-03-04 [Short Paper] High-Resolution Image Completion by Hierarchical Neural Process Masato Miyahara, Daisuke Sato, Masato Fukuda, Narimune Matsumura, Yoshiki Nishikawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Neural Process (NP) is a deep generation model which can consider the uncertainty of prediction. The unknown output is estimated by learning the stochastic expression of the original function as a latent variable using the known input/output data following the shape unknown function as learning data. On the other hand, NP assumes Gaussian distribution as a distribution followed by latent variables, so it is difficult to adapt to data following a function represented by a complex distribution with non-Gaussian latent variables. In this paper, we propose a hierarchical NP which is a hierarchical representation of the latent variables of NPs. In addition to the hierarchy of NPs, we introduce skip paths and bidirectional latent variables in order to improve the learning efficiency of latent variables in upper layers. As a result of the comparison experiment using the composite function of the linear function, it was shown that the prediction performance of the proposed method was inferior to the existing method in the simple condition setting. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Process / Hierarchization / Image Complementation / Meta Learning / Deep Learning |
| Paper # | PRMU2020-74 |
| Date of Issue | 2021-02-25 (PRMU) |
| Conference Information | |
| Committee | PRMU / IPSJ-CVIM |
|---|---|
| Conference Date | 2021/3/4(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Computer Vision and Pattern Recognition for specific environment |
| Chair | Yoichi Sato(Univ. of Tokyo) |
| Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
| Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
| Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Short Paper] High-Resolution Image Completion by Hierarchical Neural Process |
| Sub Title (in English) | |
| Keyword(1) | Neural Process |
| Keyword(2) | Hierarchization |
| Keyword(3) | Image Complementation |
| Keyword(4) | Meta Learning |
| Keyword(5) | Deep Learning |
| 1st Author's Name | Masato Miyahara |
| 1st Author's Affiliation | NTT Service Evolution Laboratories(NTT) |
| 2nd Author's Name | Daisuke Sato |
| 2nd Author's Affiliation | NTT Service Evolution Laboratories(NTT) |
| 3rd Author's Name | Masato Fukuda |
| 3rd Author's Affiliation | NTT Service Evolution Laboratories(NTT) |
| 4th Author's Name | Narimune Matsumura |
| 4th Author's Affiliation | NTT Service Evolution Laboratories(NTT) |
| 5th Author's Name | Yoshiki Nishikawa |
| 5th Author's Affiliation | NTT Service Evolution Laboratories(NTT) |
| Date | 2021-03-04 |
| Paper # | PRMU2020-74 |
| Volume (vol) | vol.120 |
| Number (no) | PRMU-409 |
| Page | pp.pp.31-34(PRMU), |
| #Pages | 4 |
| Date of Issue | 2021-02-25 (PRMU) |