Presentation 2022-06-09
Speeding-up by Reduction of Processing Paths in Octave Convolution
Akito Yoshikawa, Hidehiro Nakano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Octave Convolution (OctConv), one of the convolutional neural network methods, can also improve accuracy while reducing computational and memory costs compared to conventional convolution. On the other hand, it requires processing to separate and integrate images into different resolution components. In this study, we propose a method to reduce processing time while maintaining recognition accuracy by eliminating unnecessary processing paths in OctConv.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Machine Learning / Deep Learning / Convolution Neural Network / Image Recognition
Paper # NLP2022-6,CCS2022-6
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) Speeding-up by Reduction of Processing Paths in Octave Convolution
Sub Title (in English)
Keyword(1) Machine Learning
Keyword(2) Deep Learning
Keyword(3) Convolution Neural Network
Keyword(4) Image Recognition
1st Author's Name Akito Yoshikawa
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 # NLP2022-6,CCS2022-6
Volume (vol) vol.122
Number (no) NLP-65,CCS-66
Page pp.pp.27-30(NLP), pp.27-30(CCS),
#Pages 4
Date of Issue 2022-06-02 (NLP, CCS)