A Dynamic Adjust-Head Siamese network for object tracking

Siamese network based trackers formulate tracking as a similarity matching problem between a target template and a search region. Virtually all popular Siamese trackers use cross-correlation to measure the similarity between the deep feature of template and search image. However, the emphasis for feature extraction in different parts of the image are the same. Besides, the global matching between the template and search region also seriously neglects the part-level information and the deformation of targets during tracking. In this study, to tackle the above issues, a simple but effective Dynamic Adjust-Head (SiamDAH) model is proposed to extract features from different parts of an object. In addition, an improved pixelwise cross-correlation model (PWCC) is designed to enhance the naive cross-correlation operation to produce multiple similarity maps associated with different parts of the target. Experiments on serval challenging benchmarks including OTB-100, GOT-10k, LaSOT, and TrackingNet demonstrate that the proposed SiamDAH outperforms many state-of-the-art trackers and achieves leading performance.