Multi-label Fashion Image Classification with Minimal Human Supervision

Naoto Inoue, Edgar Simo-Serra, Toshihiko Yamasaki, Hiroshi Ishikawa

研究成果: Conference contribution

21 被引用数 (Scopus)

抄録

We tackle the problem of multi-label classification of fashion images, learning from noisy data with minimal human supervision. We present a new dataset of full body poses, each with a set of 66 binary labels corresponding to the information about the garments worn in the image obtained in an automatic manner. As the automatically-collected labels contain significant noise, we manually correct the labels for a small subset of the data, and use these correct labels for further training and evaluation. We build upon a recent approach that both cleans the noisy labels and learns to classify, and introduce simple changes that can significantly improve the performance.

本文言語English
ホスト出版物のタイトルProceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ2261-2267
ページ数7
ISBN(電子版)9781538610343
DOI
出版ステータスPublished - 2017 7 1
イベント16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italy
継続期間: 2017 10 222017 10 29

出版物シリーズ

名前Proceedings - 2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017
2018-January

Other

Other16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
国/地域Italy
CityVenice
Period17/10/2217/10/29

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Multi-label Fashion Image Classification with Minimal Human Supervision」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