A Twofold Siamese Network for Real-Time Object Tracking下载

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 similarity- learning 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 addi- tion, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed ac- cording to the channel activations around the target posi- tion. While the inherited architecture from SiamFC [3] al- lows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outper- forms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks. 1. Introduction