article · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2017

Multi-instance learning based on instance consistency for image retrieval

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

Cited by 0Abstract and details only

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.

Cite this paper

APA 7

Zhang, M., Wu, Z., Wan, S., Yue, L., & Yin, B. (2017). Multi-instance learning based on instance consistency for image retrieval. Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE, 10420, 104204J. https://doi.org/10.1117/12.2281540

MLA 9

Zhang, Miao, et al. “Multi-instance learning based on instance consistency for image retrieval.” Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE, vol. 10420, 2017, p. 104204J, https://doi.org/10.1117/12.2281540.

Chicago

Zhang, Miao, Zhize Wu, Shouhong Wan, Lihua Yue, and Bangjie Yin. 2017. “Multi-instance learning based on instance consistency for image retrieval.” Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 10420: 104204J. https://doi.org/10.1117/12.2281540.

Harvard

Zhang, M. et al. (2017) ‘Multi-instance learning based on instance consistency for image retrieval’, Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE, 10420, p. 104204J. Available at: https://doi.org/10.1117/12.2281540.

BibTeX

@article{zhang2017multi,
  title = {{Multi-instance learning based on instance consistency for image retrieval}},
  author = {Zhang, Miao and Wu, Zhize and Wan, Shouhong and Yue, Lihua and Yin, Bangjie},
  journal = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  volume = {10420},
  pages = {104204J},
  year = {2017},
  doi = {10.1117/12.2281540}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.