Share Email Print
cover

Proceedings Paper • new

Multi-instance learning based on instance consistency for image retrieval
Author(s): Miao Zhang; Zhize Wu; Shouhong Wan; Lihua Yue; Bangjie Yin
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Multiple-instance learning (MIL) has been successfully utilized in image retrieval. Existing approaches cannot select positive instances correctly from positive bags which may result in a low accuracy. In this paper, we propose a new image retrieval approach called multiple instance learning based on instance-consistency (MILIC) to mitigate such issue. First, we select potential positive instances effectively in each positive bag by ranking instance-consistency (IC) values of instances. Then, we design a feature representation scheme, which can represent the relationship among bags and instances, based on potential positive instances to convert a bag into a single instance. Finally, we can use a standard single-instance learning strategy, such as the support vector machine, for performing object-based image retrieval. Experimental results on two challenging data sets show the effectiveness of our proposal in terms of accuracy and run time.

Paper Details

Date Published: 21 July 2017
PDF: 5 pages
Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104204J (21 July 2017); doi: 10.1117/12.2281540
Show Author Affiliations
Miao Zhang, Univ. of Science and Technology of China (China)
Zhize Wu, Univ. of Science and Technology of China (China)
Shouhong Wan, Univ. of Science and Technology of China (China)
Lihua Yue, Univ. of Science and Technology of China (China)
Bangjie Yin, Univ. of Science and Technology of China (China)


Published in SPIE Proceedings Vol. 10420:
Ninth International Conference on Digital Image Processing (ICDIP 2017)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top