Presentation | 2022-06-09 Basic Performance of CNNs Using Dynamic Filters Based on Octave Convolution Kiyotaka Matono, Hidehiro Nakano, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The methods of using dynamic filters for convolutional neural networks (CNNs) have attracted attentions. In recent years, CNNs have become easier to train large networks, and their performance can be further improved. On the other hand, however, there is a trade-off between the performance improvement with larger networks and the increase in computational complexity. In this study, we propose a method to separate input images into high-resolution and low-resolution components and to apply a dynamic filter to each component. The proposed method can reduce the computational complexity while minimizing the degradation of recognition rate. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | convolutional neural networks / dynamic filters / octave convolution |
Paper # | NLP2022-5,CCS2022-5 |
Date of Issue | 2022-06-02 (NLP, CCS) |
Conference Information | |
Committee | CCS / NLP |
---|---|
Conference Date | 2022/6/9(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Megumi Akai(Hokkaido Univ.) / Akio Tsuneda(Kumamoto Univ.) |
Vice Chair | Masaki Aida(TMU) / Hidehiro Nakano(Tokyo City Univ.) / Hiroyuki Torikai(Hosei Univ.) |
Secretary | Masaki Aida(TDK) / Hidehiro Nakano(Shibaura Insti. of Tech.) / Hiroyuki Torikai(Sojo Univ.) |
Assistant | Tomoyuki Sasaki(Shonan Instit. of Tech.) / Hiroyasu Ando(Tsukuba Univ.) / Miki Kobayashi(Rissho Univ.) / " Hiroyuki YASUDA(The Univ. of Tokyo) / Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.) |
Paper Information | |
Registration To | Technical Committee on Complex Communication Sciences / Technical Committee on Nonlinear Problems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Basic Performance of CNNs Using Dynamic Filters Based on Octave Convolution |
Sub Title (in English) | |
Keyword(1) | convolutional neural networks |
Keyword(2) | dynamic filters |
Keyword(3) | octave convolution |
1st Author's Name | Kiyotaka Matono |
1st Author's Affiliation | Tokyo City University(Tokyo City Univ.) |
2nd Author's Name | Hidehiro Nakano |
2nd Author's Affiliation | Tokyo City University(Tokyo City Univ.) |
Date | 2022-06-09 |
Paper # | NLP2022-5,CCS2022-5 |
Volume (vol) | vol.122 |
Number (no) | NLP-65,CCS-66 |
Page | pp.pp.23-26(NLP), pp.23-26(CCS), |
#Pages | 4 |
Date of Issue | 2022-06-02 (NLP, CCS) |