Robust Semantic Segmentation for Street Fashion Photos

Anh H. Dang*, Wataru Kameyama

*この研究の対応する著者

研究成果: Conference contribution

抄録

In this paper, we aim to produce the state-of-the-art semantic segmentation for street fashion photos with three contributions. Firstly, we propose a high-performance semantic segmentation network that follows the encoder-decoder structure. Secondly, we propose a guided training process using multiple auxiliary losses. And thirdly, the 2D max-pooling-based scaling operation to produce segmentation feature maps for the aforementioned guided training process. We also propose mIoU+ metric taking noise into account for better evaluation. Evaluations with the ModaNet data set show that the proposed network achieves high benchmark results with less computational cost compared to ever-proposed methods.

本文言語English
ホスト出版物のタイトル22nd International Conference on Advanced Communications Technology
ホスト出版物のサブタイトルDigital Security Global Agenda for Safe Society, ICACT 2020 - Proceeding
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1248-1257
ページ数10
ISBN(電子版)9791188428045
DOI
出版ステータスPublished - 2020 2月
イベント22nd International Conference on Advanced Communications Technology, ICACT 2020 - Pyeongchang, Korea, Republic of
継続期間: 2020 2月 162020 2月 19

出版物シリーズ

名前International Conference on Advanced Communication Technology, ICACT
2020
ISSN(印刷版)1738-9445

Conference

Conference22nd International Conference on Advanced Communications Technology, ICACT 2020
国/地域Korea, Republic of
CityPyeongchang
Period20/2/1620/2/19

ASJC Scopus subject areas

  • 電子工学および電気工学

フィンガープリント

「Robust Semantic Segmentation for Street Fashion Photos」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル