| Presentation | 2017-10-12 Accelerating Convolutional Neural Networks Using Low-Rank Tensor Decomposition Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In the image recognition using convolution neural networks (CNN), convolution operations occupies the majority of the computation time. In order to cope with this problem, methods which compress the dense tensors in convolution layers using low-rank approximation have been proposed to reduce the amount of computation, but these studies have not revealed the trade-off between the computational complexity reduced by low-rank approximation and the image recognition accuracy. In this research, we investigated the trade-off between the image recognition accuracy and speed-up rate for the method proposed by Peisong Wang et al. on GPU. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | image recognition / convolutional neural networks / low-rank approximation / tensor decomposition |
| Paper # | PRMU2017-63 |
| Date of Issue | 2017-10-05 (PRMU) |
| Conference Information | |
| Committee | PRMU |
|---|---|
| Conference Date | 2017/10/12(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Accelerating Convolutional Neural Networks Using Low-Rank Tensor Decomposition |
| Sub Title (in English) | |
| Keyword(1) | image recognition |
| Keyword(2) | convolutional neural networks |
| Keyword(3) | low-rank approximation |
| Keyword(4) | tensor decomposition |
| 1st Author's Name | Kazuki Osawa |
| 1st Author's Affiliation | Tokyo Institute of Technology(Tokyo Inst. of Tech.) |
| 2nd Author's Name | Akira Sekiya |
| 2nd Author's Affiliation | Tokyo Institute of Technology(Tokyo Inst. of Tech.) |
| 3rd Author's Name | Hiroki Naganuma |
| 3rd Author's Affiliation | Tokyo Institute of Technology(Tokyo Inst. of Tech.) |
| 4th Author's Name | Rio Yokota |
| 4th Author's Affiliation | Tokyo Institute of Technology(Tokyo Inst. of Tech.) |
| Date | 2017-10-12 |
| Paper # | PRMU2017-63 |
| Volume (vol) | vol.117 |
| Number (no) | PRMU-238 |
| Page | pp.pp.1-6(PRMU), |
| #Pages | 6 |
| Date of Issue | 2017-10-05 (PRMU) |