Good recognition is non-metric
详细信息 查看全文
- 作者：Walter J. Scheirera ; e ; wscheirer@fas.harvard.edu" class="auth_mailAuthor Vitae ; Michael J. Wilberb ; mjw285@cornell.edu" class="auth_mailAuthor Vitae ; Michael Eckmannc ; meckmann@skidmore.edu" class="auth_mailAuthor Vitae ; Terrance E. Boultd ; e ; tboult@securics.com" class="auth_mailAuthor Vitae
- 关键词：Machine learning ; Metric learning ; Recognition ; Computer vision ; Face recognition ; Object recognition
- 刊名：Pattern Recognition
- 出版年：August 2014
- 年：2014
- 卷：47
- 期：8
- 页码：2721-2731
- 全文大小：1070 K
文摘
- •
A thorough and critical review of the most recent literature in metric learning and related fields.
- •
A new general definition of recognition that is not restricted to pair matching.
- •
An extensive meta-analysis of metric learning on Caltech 101 and Labeled Faces in the Wild.
- •
An experimental evaluation of top performing metric and non-metric algorithms.
- •
A series of useful recommendations, based on our results, for recognition algorithm designs.