Multi-instance learning based on instance consistency for image retrieval

Miao Zhang; Zhize Wu; Shouhong Wan; Lihua Yue; Bangjie Yin

doi:10.1117/12.2281540

21 July 2017 Multi-instance learning based on instance consistency for image retrieval

Miao Zhang, Zhize Wu, Shouhong Wan, Lihua Yue, Bangjie Yin

Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104204J (2017) https://doi.org/10.1117/12.2281540
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China

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.

Citation Download Citation

Miao Zhang, Zhize Wu, Shouhong Wan, Lihua Yue, and Bangjie Yin "Multi-instance learning based on instance consistency for image retrieval", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104204J (21 July 2017); https://doi.org/10.1117/12.2281540

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available