Robust Semantic Segmentation for Street Fashion Photos

研究成果: Conference contribution

抜粋

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.

元の言語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
出版者Institute of Electrical and Electronics Engineers Inc.
ページ1248-1257
ページ数10
ISBN(電子版)9791188428045
DOI
出版物ステータスPublished - 2020 2
イベント22nd International Conference on Advanced Communications Technology, ICACT 2020 - Pyeongchang, Korea, Republic of
継続期間: 2020 2 162020 2 19

出版物シリーズ

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

Conference

Conference22nd International Conference on Advanced Communications Technology, ICACT 2020
Korea, Republic of
Pyeongchang
期間20/2/1620/2/19

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

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。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Dang, A. H., & Kameyama, W. (2020). Robust Semantic Segmentation for Street Fashion Photos. : 22nd International Conference on Advanced Communications Technology: Digital Security Global Agenda for Safe Society, ICACT 2020 - Proceeding (pp. 1248-1257). [9061408] (International Conference on Advanced Communication Technology, ICACT; 巻数 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ICACT48636.2020.9061408