Object semantic-guided graph attention feature fusion network for Siamese visual tracking

The similarity matching between the template and the search area plays a key role in Siamese-based trackers. Most Siamese-based trackers adopt correlation operation to perform feature fusion on the template branch and search branch for similarity matching. However, the correlation operation directly uses the template feature to slide the window on the search area feature without distinguishing the discriminant part of the target and the background noise, which blurs the spatial information of the response feature. To address this issue, this work proposes a novel object semantic-guided graph attention feature fusion network that both removes background information and focuses on the discriminative part of the object. The proposed network effectively removes background noise by utilizing an adaptive template instead of the fixed-size template used by the correlation operation. The network also models the contextual semantic relations of the target and uses the resulting semantic relations to guide the feature fusion process in a part-based manner, thereby accurately highlighting the discriminative parts of the target. Therefore, the problem of blurring response feature caused by correlation operation is effectively resolved. Furthermore, we propose an object-aware prediction network to learn object-aware features for classification and regression task, which effectively improves the discriminative ability of the prediction network. Experiments on many challenging benchmarks like OTB-100, LaSOT, TColor-128, GOT-10k and VOT2019, show that our methods achieves excellent performance.