Presentation | 2018-02-16 Parallel feature pooling without information loss Akito Takeki, Daiki Ikami, Go Irie, Kiyoharu Aizawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In convolutional neural networks for image recognition, the pooling layer plays a important role. The pooling layer performs downsampling in order to acquire the shift invariance and reduce the calculation amount. But at the same time, it discards a lot of useful information for training. In this paper, we propose a novel pooling method called Parallel Grid pooling (PGP). Experimental results on several popular image classification benchmarks show the effectiveness of the proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Pooling / Data Augmentation / Convolutional Neural Networks / Image Classification |
Paper # | ITS2017-80,IE2017-112 |
Date of Issue | 2018-02-08 (ITS, IE) |
Conference Information | |
Committee | ITS / IE / ITE-MMS / ITE-HI / ITE-ME / ITE-AIT |
---|---|
Conference Date | 2018/2/15(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Hokkaido Univ. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image Processing, etc. |
Chair | Takayoshi Yokota(Tottori Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Norihiko Ishii(NHK) / Masayuki Sato(Univ. of Kitakyushu) / Miki Haseyama(Hokkaido Univ.) / Nobuhiko Mukai(Tokyo Cisy Univ.) |
Vice Chair | Masahiro Fujii(Utsunomiya Univ.) / Tomotaka Wada(Kansai Univ.) / Kazuya Kodama(NII) / Hideaki Kimata(NTT) / / / Norio Tagawa(Tokyo Metropolitan Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.) |
Secretary | Masahiro Fujii(Meiji Univ.) / Tomotaka Wada(Saitama Univ.) / Kazuya Kodama(Nagoya Univ.) / Hideaki Kimata(KDDI Research) / (NHK) / (NTT) / Norio Tagawa(NHK) / Hisaki Nate(NHK) |
Assistant | Msataka Imao(ME) / Yanlei Gu(Univ. of Tokyo) / Kenshi Saho(Toyama Prefectural Univ.) / Kouichiro Hashiura(Akita Prefectural Univ.) / Yasutaka Matsuo(NHK) / Kazuya Hayase(NTT) |
Paper Information | |
Registration To | Technical Committee on Intelligent Transport Systems Technology / Technical Committee on Image Engineering / Technical Group on Multi-media Storage / Technical Group on Human Inormation / Technical Group on Media Engineering / Technical Group on Artistic Image Technology |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Parallel feature pooling without information loss |
Sub Title (in English) | |
Keyword(1) | Pooling |
Keyword(2) | Data Augmentation |
Keyword(3) | Convolutional Neural Networks |
Keyword(4) | Image Classification |
1st Author's Name | Akito Takeki |
1st Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
2nd Author's Name | Daiki Ikami |
2nd Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
3rd Author's Name | Go Irie |
3rd Author's Affiliation | NTT Communication Science Laboratories(NTT) |
4th Author's Name | Kiyoharu Aizawa |
4th Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
Date | 2018-02-16 |
Paper # | ITS2017-80,IE2017-112 |
Volume (vol) | vol.117 |
Number (no) | ITS-431,IE-432 |
Page | pp.pp.239-244(ITS), pp.239-244(IE), |
#Pages | 6 |
Date of Issue | 2018-02-08 (ITS, IE) |