Mining Discriminative Triplets of Patches for Fine-Grained Classification

被引：101

作者：

Wang, Yaming ^{[1
]}

Choi, Jonghyun ^{[2
]}

Morariu, Vlad I. ^{[1
]}

Davis, Larry S. ^{[1
]}

机构：

[1] Univ Maryland, College Pk, MD 20742 USA

[2] Comcast Labs DC, Washington, DC 20005 USA

来源：

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2016年

关键词：

D O I：

10.1109/CVPR.2016.131

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or achieves comparable performance to the state-of-the-art in classification.

引用

页码：1163 / 1172

页数：10