Fashion style in 128 floats: Joint ranking and classification using weak data for feature extraction

研究成果: Conference contribution

90 被引用数 (Scopus)

抄録

We propose a novel approach for learning features from weakly-supervised data by joint ranking and classification. In order to exploit data with weak labels, we jointly train a feature extraction network with a ranking loss and a classification network with a cross-entropy loss. We obtain high-quality compact discriminative features with few parameters, learned on relatively small datasets without additional annotations. This enables us to tackle tasks with specialized images not very similar to the more generic ones in existing fully-supervised datasets. We show that the resulting features in combination with a linear classifier surpass the state-of-the-art on the Hipster Wars dataset despite using features only 0.3% of the size. Our proposed features significantly outperform those obtained from networks trained on ImageNet, despite being 32 times smaller (128 single-precision floats), trained on noisy and weakly-labeled data, and using only 1.5% of the number of parameters.1.

本文言語English
ホスト出版物のタイトルProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
出版社IEEE Computer Society
ページ298-307
ページ数10
ISBN(電子版)9781467388504
DOI
出版ステータスPublished - 2016 12 9
イベント29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
継続期間: 2016 6 262016 7 1

出版物シリーズ

名前Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2016-December
ISSN(印刷版)1063-6919

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period16/6/2616/7/1

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

フィンガープリント 「Fashion style in 128 floats: Joint ranking and classification using weak data for feature extraction」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