Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels

Ryusuke Miyamoto, Takeshi Nakajima, Takuro Oki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

To improve the accuracy of fashion style estimation, this paper proposes anovel large-scale dataset named WEARStyle and twotypesofnovel schemes that remove unnecessary pixels: SSD-based human detection and PSPNet-based pixel selection. The classification accuracy ofthe Hipster Wars dataset is improved to78.8%byan SVM-based classifier when the WEARStyle dataset isusedto train a ResNet50-based feature extractor. The accuracy is improved to80.0% and 80.9%, when the SSD-based human detection and PSPNet-based pixel selection are applied, respectively. The achieved accuracy outperforms thoseof other existing schemes.

Original languageEnglish
Title of host publication2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728103976
DOIs
Publication statusPublished - 1 Jan 2019
Event2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan
Duration: 26 May 201929 May 2019

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2019-May
ISSN (Print)0271-4310

Conference

Conference2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
CountryJapan
CitySapporo
Period26/05/1929/05/19

Fingerprint

Pixels
Classifiers

Cite this

Miyamoto, R., Nakajima, T., & Oki, T. (2019). Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings [8702560] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2019.8702560
Miyamoto, Ryusuke ; Nakajima, Takeshi ; Oki, Takuro. / Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{204b4ee4fccc4d4fa24378309528f6ba,
title = "Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels",
abstract = "To improve the accuracy of fashion style estimation, this paper proposes anovel large-scale dataset named WEARStyle and twotypesofnovel schemes that remove unnecessary pixels: SSD-based human detection and PSPNet-based pixel selection. The classification accuracy ofthe Hipster Wars dataset is improved to78.8{\%}byan SVM-based classifier when the WEARStyle dataset isusedto train a ResNet50-based feature extractor. The accuracy is improved to80.0{\%} and 80.9{\%}, when the SSD-based human detection and PSPNet-based pixel selection are applied, respectively. The achieved accuracy outperforms thoseof other existing schemes.",
author = "Ryusuke Miyamoto and Takeshi Nakajima and Takuro Oki",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ISCAS.2019.8702560",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",

}

Miyamoto, R, Nakajima, T & Oki, T 2019, Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702560, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 26/05/19. https://doi.org/10.1109/ISCAS.2019.8702560

Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels. / Miyamoto, Ryusuke; Nakajima, Takeshi; Oki, Takuro.

2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8702560 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels

AU - Miyamoto, Ryusuke

AU - Nakajima, Takeshi

AU - Oki, Takuro

PY - 2019/1/1

Y1 - 2019/1/1

N2 - To improve the accuracy of fashion style estimation, this paper proposes anovel large-scale dataset named WEARStyle and twotypesofnovel schemes that remove unnecessary pixels: SSD-based human detection and PSPNet-based pixel selection. The classification accuracy ofthe Hipster Wars dataset is improved to78.8%byan SVM-based classifier when the WEARStyle dataset isusedto train a ResNet50-based feature extractor. The accuracy is improved to80.0% and 80.9%, when the SSD-based human detection and PSPNet-based pixel selection are applied, respectively. The achieved accuracy outperforms thoseof other existing schemes.

AB - To improve the accuracy of fashion style estimation, this paper proposes anovel large-scale dataset named WEARStyle and twotypesofnovel schemes that remove unnecessary pixels: SSD-based human detection and PSPNet-based pixel selection. The classification accuracy ofthe Hipster Wars dataset is improved to78.8%byan SVM-based classifier when the WEARStyle dataset isusedto train a ResNet50-based feature extractor. The accuracy is improved to80.0% and 80.9%, when the SSD-based human detection and PSPNet-based pixel selection are applied, respectively. The achieved accuracy outperforms thoseof other existing schemes.

UR - http://www.scopus.com/inward/record.url?scp=85066780279&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702560

DO - 10.1109/ISCAS.2019.8702560

M3 - Conference contribution

AN - SCOPUS:85066780279

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Miyamoto R, Nakajima T, Oki T. Accuratefashion style estimationwitha novel training set and removal of unnecessary pixels. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8702560. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2019.8702560