Share Email Print

Proceedings Paper

A similarity learning for fine-grained images based on the Mahalanobis metric and the kernel method
Author(s): Zisheng Fu; Ninghua Wang; Zhimin Feng; Ting Dong
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Since most prior studies on similar image retrieval focused on the category level, image similarity learning at the finegrained level remains challenge, which often leads to a semantic gap between the low-level visual features and highlevel human perception. To solve the problem, we proposed a Mahalanobis and kernel-based similarity (Mah-Ker) method combined with features developed by the Convolutional Neural Network (CNN). Firstly, triplet constraints are introduced to characterize the fine-grained image similarity relationship which the Mahalanobis metric is trained upon. Then a kernel-based metric is proposed in the last layer of model to devise nonlinear extensions of Mahalanobis metric and further enhance the performance. Experiments based on the real dress dataset showed that our proposed method achieved a promising higher retrieval performance than both the state-of-art fine-grained similarity model and the hand-crafted visual feature based approaches.

Paper Details

Date Published: 26 July 2018
PDF: 6 pages
Proc. SPIE 10828, Third International Workshop on Pattern Recognition, 1082815 (26 July 2018); doi: 10.1117/12.2501757
Show Author Affiliations
Zisheng Fu, Vipshop China (China)
Ninghua Wang, Vipshop US Inc. (United States)
Zhimin Feng, Vipshop China (China)
Ting Dong, Vipshop China (China)

Published in SPIE Proceedings Vol. 10828:
Third International Workshop on Pattern Recognition
Xudong Jiang; Zhenxiang Chen; Guojian Chen, Editor(s)

© SPIE. Terms of Use
Back to Top