How do Convolutional Neural Networks Learn Design?

Shailza Jolly, Brian Kenji Iwana, Ryohei Kuroki, Seiichi Uchida

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

7 被引用数 (Scopus)

抄録

In this paper, we aim to understand the design principles in book cover images which are carefully crafted by experts. Book covers are designed in a unique way, specific to genres which convey important information to their readers. By using Convolutional Neural Networks (CNN) to predict book genres from cover images, visual cues which distinguish genres can be highlighted and analyzed. In order to understand these visual clues contributing towards the decision of a genre, we present the application of Layer-wise Relevance Propagation (LRP) on the book cover image classification results. We use LRP to explain the pixel-wise contributions of book cover design and highlight the design elements contributing towards particular genres. In addition, with the use of state-of-the-art object and text detection methods, insights about genre-specific book cover designs are discovered.

本文言語英語
ホスト出版物のタイトル2018 24th International Conference on Pattern Recognition, ICPR 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1085-1090
ページ数6
ISBN(電子版)9781538637883
DOI
出版ステータス出版済み - 11 26 2018
イベント24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, 中国
継続期間: 8 20 20188 24 2018

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
2018-August
ISSN(印刷版)1051-4651

その他

その他24th International Conference on Pattern Recognition, ICPR 2018
国/地域中国
CityBeijing
Period8/20/188/24/18

All Science Journal Classification (ASJC) codes

  • 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

「How do Convolutional Neural Networks Learn Design?」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