Multi-Task Convolutional Neural Network Leading to High Performance and Interpretability via Attribute Estimation

Maeda, Keisuke; Horii, Kazaha; Ogawa, Takahiro; Haseyama, Miki

doi:10.1587/transfun.2020SML0006


Hokkaido University \| Library \| HUSCAP	Advanced Search		言語

	Home
	About HUSCAP
	Open Access Policy

	Browse by Author

Browse
	Communities & Collections

	Scholarly Journals
	Theses
	Doctoral Dissertations Listed by Graduate Schools
	Conference Procs.
	Events

	HUSCAP Senior (in Japanese)

	Societies

	Downloads (country)

For university staff
	How to post your papers to HUSCAP
	Publication of theses
	Helpline about theses publication

Open Archives Compliant

You can search our collection also at:
	Google
	Google Scholar
	CiNii
	IRDB
	OAIster
	NDLTD

Hokkaido University Collection of Scholarly and Academic Papers >
Office of Institutional Research >
Peer-reviewed Journal Articles, etc >

Multi-Task Convolutional Neural Network Leading to High Performance and Interpretability via Attribute Estimation

Files in This Item:

2020-12-01_Multi-ta.pdf

930.68 kB

PDF

View/Open

Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/80378

Title:	Multi-Task Convolutional Neural Network Leading to High Performance and Interpretability via Attribute Estimation
Authors:	Maeda, Keisuke Browse this author
	Horii, Kazaha Browse this author
	Ogawa, Takahiro Browse this author →KAKEN DB
	Haseyama, Miki Browse this author →KAKEN DB
Keywords:	multi-task convolutional neural network
	image classification
	attribute estimation
	interpretability
Issue Date:	Dec-2020
Publisher:	電子情報通信学会(The Institute of Electronics, Information and Communication Engineers / IEICE)
Journal Title:	IEICE transactions on fundamentals of electronics communications and computer sciences
Volume:	E103A
Issue:	12
Start Page:	1609
End Page:	1612
Publisher DOI:	10.1587/transfun.2020SML0006
Abstract:	A multi-task convolutional neural network leading to high performance and interpretability via attribute estimation is presented in this letter. Our method can provide interpretation of the classification results of CNNs by outputting attributes that explain elements of objects as a judgement reason of CNNs in the middle layer. Furthermore, the proposed network uses the estimated attributes for the following prediction of classes. Consequently, construction of a novel multi-task CNN with improvements in both of the interpretability and classification performance is realized.
Rights:	copyright©2020 IEICE
Rights:	http://search.ieice.org/
Type:	article
URI:	http://hdl.handle.net/2115/80378
Appears in Collections:	総合IR本部 (Office of Institutional Research) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 前田圭介

OAI-PMH ( junii2 , jpcoar_1.0 )

- Hokkaido University