Kyushu Institute of Technology Academic Repository
Kyutacarは九州工業大学で生産された研究成果を オープンアクセスで提供する機関リポジトリシステムです。 Kyutacar is open-access repository of research by members of the Kyushu Institute of Technology.
Department of Mechanical and Control Engineering, Graduate School of Engineering, Kyushu Institute of Technology, Fukuoka, Japan
Faculty of Engineering, Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Fukuoka, Japan
抄録
In this paper, we propose a FTOP (Feature Transform Optimization Problem) and its solution. We propose a method to optimize both parameters and processing order of feature transform simultaneously, not limited to convolution and pooling included in CNN (Convolutional Neural Network). In order to realize the optimization, we formulate it as a combinatorial optimization problem and solve it by meta-heuristics. The effectiveness of the proposed method is shown by applying the proposed method to pedestrian classification based on a benchmark data set.
内容記述
SICE Annual Conference 2018 (SICE 2018), September 11–14, 2018, Nara, Japan
雑誌名
2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE)
発行年
2018-09-11
出版者
IEEE
ISBN
978-4-907764-60-9
978-1-5386-6644-9
DOI
http://dx.doi.org/10.23919/SICE.2018.8492633
権利
Copyright (c) 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Feature Transform Optimization for Pedestrian Classification
10328694.pdf
(432.74KB)
