Online object tracking based interactive attention

By embedding Transformer into the Siamese tracking framework, some Transformer-based Siamese tracking network are proposed, such as TransT and SwinTrack. Nevertheless, the existing Transformer-based Siamese tracking networks do not fully utilize the object information of template branch, and their position encoding methods cannot accurately perceive the object position. Aiming at these problems, a novel Transformer-based Siamese tracking network, which includes feature extraction, feature fusion and prediction head, is proposed in this work. Firstly, an interactive attention calculation module for template branch and search branch is designed to enhance the feature extraction capability of the network for the object region and suppress the background interference. In addition, to address the problem that the existing Transformer-based feature fusion network is not sensitive enough to the object location region, a position encoding method that characterizes the relative distance is proposed to enhance the perception ability of the object location and reduce network parameters. Then, the contrastive loss is introduced to enhance the discriminative ability of the classification layer between foreground and background, and to effectively deal with the interference of similar objects in the background. Extensive experiments with state-of-the-art trackers are carried out on four challenging visual object tracking benchmarks: GOT-10k, LaSOText, TLP, and TrackingNet. Experimental results demonstrate the proposed method is more robust on multiple challenges and can achieve considerable performances with AO of 70.1% on GOT-10k, SUC score of 45.5% on LaSOT ext ,56.9% on TLP, and 79.7% on TrackingNet datasets. It runs faster (7.1G MACs) and occupies less memory (21M), making it more suitable for practical applications.

Automated summary

This paper proposes a Transformer-based Siamese tracking network that addresses the issues of underutilization of object information and inaccurate position encoding in existing networks. The proposed network includes feature extraction, feature fusion, and prediction head modules to enhance feature extraction capability and perception ability of the network. Experimental results demonstrate improved tracking performance on various challenging benchmarks.