A Twofold Siamese Network for Real-Time Object Tracking

Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance b...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 4834 - 4843
Main Authors He, Anfeng, Luo, Chong, Tian, Xinmei, Zeng, Wenjun
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Feature extraction
Object tracking
Real-time systems
Semantics
Target tracking
Task analysis
Training
Online AccessGet full text
ISSN1063-6919
DOI10.1109/CVPR.2018.00508

Cover

More Information
Summary:Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similaritylearning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC [3] allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00508