SGAT: Shuffle and graph attention based Siamese networks for visual tracking

• Published in: PloS one Vol. 17; no. 11; p. e0277064
• Main Authors: Wang, Jun, Zhang, Limin, Zhang, Wenshuang, Wang, Yuanyun, Deng, Chengzhi
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 23.11.2022; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Analysis; Artificial neural networks; Benchmarks; Biology and Life Sciences; Computer and Information Sciences; Correlation; Cross correlation; Engineering and Technology; Exploitation; Feature extraction; Graph matching; Learning; Neural networks; Neural Networks, Computer; Occlusion; Optical tracking; Physical Sciences; Research and Analysis Methods; Searching; Similarity; Social Sciences; China
• DOI: 10.1371/journal.pone.0277064
• ISSN: 1932-6203

Siamese-based trackers have achieved excellent performance and attracted extensive attention, which regard the tracking task as a similarity learning between the target template and search regions. However, most Siamese-based trackers do not effectively exploit correlations of the spatial and channel-wise information to represent targets. Meanwhile, the cross-correlation is a linear matching method and neglects the structured and part-level information. In this paper, we propose a novel tracking algorithm for feature extraction of target templates and search region images. Based on convolutional neural networks and shuffle attention, the tracking algorithm computes the similarity between the template and a search region through a graph attention matching. The proposed tracking algorithm exploits the correlations between the spatial and channel-wise information to highlight the target region. Moreover, the graph matching can greatly alleviate the influences of appearance variations such as partial occlusions. Extensive experiments demonstrate that the proposed tracking algorithm achieves excellent tracking results on multiple challenging benchmarks. Compared with other state-of-the-art methods, the proposed tracking algorithm achieves excellent tracking performance.