Multi-granularity Hierarchical Attention Siamese Network for Visual Tracking

Xing Chen, Xiang Zhang, Huibin Tan, Long Lan, Zhigang Luo, Xuhui HuangIJCNN 2018 · OpenReview

Abstract

Speed and accuracy are the two most important focuses for many visual tracking methods. Recently, siamese networks based trackers have shown very promising potentials in both aspects, which develop a twin network to measure the responses between target and hypotheses with a fully convolutional operation. However, the learned response maps are vulnerable to background clutters and scale changes as they ignore priori knowledge such as the object salience and multi-granularity cues. To explore the benefits of priori, this paper devises a multi-granularity hierarchical attention siamese network tracker (MHA-Siam) to further enhance the tracking stability without sacrificing real-time speed. Particularly, the channel-wise attention mechanism is exploited here to filter out the background while remain the salient object region; then, the response maps of the coarse-to-finer multi-layer features are fused to capture multi-granularity location information helpful for improvement in tracking stability. To make full use of them, MHA-Siam imposes the element-wise max-and-sum operation on them to induce a reliable response map for accurate location. Experiments of visual tracking on OTB benchmark shows the superiority of MHA-Siam with the competitive efficiency to its counterpart trackers.
BibTeX
@inproceedings{chen2018multi,
  author = {Xing Chen and Xiang Zhang and Huibin Tan and Long Lan and Zhigang Luo and Xuhui Huang},
  title = {{Multi-granularity Hierarchical Attention Siamese Network for Visual Tracking}},
  booktitle = {IJCNN},
  year = {2018},
  url = {https://openreview.net/forum?id=nLPZXZWIIp},
}

Loading related content...

Figure