Multi-level Cross-attention Siamese Network For Visual Object Tracking

• Jianwei Zhang,
• Jingchao Wang,
• Huanlong Zhang,
• Mengen Miao,
• Zengyu Cai,
• Fuguo Chen,

Vol. 16, No. 12, December 31, 2022
10.3837/tiis.2022.12.011, Download Paper (Free):

• computer vision
• object tracking
• Cross-attention
• self-attention
• Siamese Network

Abstract

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

Statistics

Cite this article