Learning discriminative and shareable patches for scene classification

Shoucheng Ni, Qieshi Zhangg, Sei Ichiro Kamata, Chongyang Zhang

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

This paper addresses the problem of scene classification and proposes learning discriminative and shareable patches (LDSP) method. The main idea of learning discriminative and shareable patches is to discover patches that exhibit both large between-class dissimilarity (discriminative) and large within-class similarity (shareable). A novel and efficient re-clustering, based on co-occurrence relationship of first-step clustering, is proposed and conducted to further enhance the visual similarity of patches within each cluster. In order to establish appropriate criteria for selecting desired patches, a condensed representation of image features called feature epitome is introduced. In the classification, a patch feature involving pre-trained convolutional neural network model is investigated. The experimental result outperforms existing single-feature methods on MIT 67 scene benchmark in term of mean Accuracy Precision.

本文言語English
ホスト出版物のタイトル2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1317-1321
ページ数5
ISBN(電子版)9781479999880
DOI
出版ステータスPublished - 2016 5 18
イベント41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
継続期間: 2016 3 202016 3 25

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2016-May
ISSN(印刷版)1520-6149

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
国/地域China
CityShanghai
Period16/3/2016/3/25

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Learning discriminative and shareable patches for scene classification」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