中文|CAS

logo
banner

Journals & Publications

Publications Papers

Papers

Multi-View 3D Object Retrieval With Deep Embedding Network
Dec 16, 2016Author：
PrintText Size A A

*Click Here to View Full Record
Title: Multi-View 3D Object Retrieval With Deep Embedding Network
Authors: Guo, HY; Wang, JQ; Gao, Y; Li, JQ; Lu, HQ
Author Full Names: Guo, Haiyun; Wang, Jinqiao; Gao, Yue; Li, Jianqiang; Lu, Hanqing
Source: IEEE TRANSACTIONS ON IMAGE PROCESSING, 25 (12):5526-5537; 10.1109/TIP.2016.2609814 DEC 2016
Language: English
Abstract: In multi-view 3D object retrieval, each object is characterized by a group of 2D images captured from different views. Rather than using hand-crafted features, in this paper, we take advantage of the strong discriminative power of convolutional neural network to learn an effective 3D object representation tailored for this retrieval task. Specifically, we propose a deep embedding network jointly supervised by classification loss and triplet loss to map the high-dimensional image space into a low-dimensional feature space, where the Euclidean distance of features directly corresponds to the semantic similarity of images. By effectively reducing the intra-class variations while increasing the inter-class ones of the input images, the network guarantees that similar images are closer than dissimilar ones in the learned feature space. Besides, we investigate the effectiveness of deep features extracted from different layers of the embedding network extensively and find that an efficient 3D object representation should be a tradeoff between global semantic information and discriminative local characteristics. Then, with the set of deep features extracted from different views, we can generate a comprehensive description for each 3D object and formulate the multi-view 3D object retrieval as a set-to-set matching problem. Extensive experiments on SHREC'15 data set demonstrate the superiority of our proposed method over the previous state-of-the-art approaches with over 12% performance improvement.
ISSN: 1057-7149
eISSN: 1941-0042
IDS Number: EC5VJ
Unique ID: WOS:000388205100002