論文

査読有り
2012年9月

On Taxonomies for Multi-class Image Categorization

INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Alexander Binder
  • ,
  • Klaus-Robert Mueller
  • ,
  • Motoaki Kawanabe

99
3
開始ページ
281
終了ページ
301
記述言語
英語
掲載種別
研究論文(学術雑誌)
DOI
10.1007/s11263-010-0417-8
出版者・発行元
SPRINGER

We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines (SVMs) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local SVMs might be of high practical use. Further empirical results on subsets of Caltech256 and VOC2006 data indeed show that our local SVM formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.

Web of Science ® 被引用回数 : 23

リンク情報
DOI
https://doi.org/10.1007/s11263-010-0417-8
Web of Science
https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000304655600003&DestApp=WOS_CPL
URL
http://dblp.uni-trier.de/db/journals/ijcv/ijcv99.html#journals/ijcv/BinderMK12
ID情報
  • DOI : 10.1007/s11263-010-0417-8
  • ISSN : 0920-5691
  • DBLP ID : journals/ijcv/BinderMK12
  • Web of Science ID : WOS:000304655600003

エクスポート
BibTeX RIS