Transformer Tracking with Cyclic Shifting Window Attention
Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and unavoidably ignore the integrity of objects. In this paper, we propose a new transformer architecture with multi-scale cyclic shifting window attention for visual object tracking, elevating the attention from pixel to window level. The cross-window multi-scale attention has the advantage of aggregating attention at different scales and generates the best fine-scale match for the target object. Furthermore, the cyclic shifting strategy brings greater accuracy by expanding the window samples with positional information, and at the same time saves huge amounts of computational power by removing redundant calculations. Extensive experiments demonstrate the superior performance of our method, which also sets the new state-of-the-art records on five challenging datasets, along with the VOT2020, UAV123, LaSOT, TrackingNet, and GOT-10k benchmarks.
Code (1)
Tasks
ObjectObject TrackingVisual Object TrackingSimilar Papers 제목 키워드 기반
Swin-Free: Achieving Better Cross-Window Attention and Efficiency with Size-varying Window
Transformer models have shown great potential in computer vision, following their success in language tasks. Swin Transformer is one of them that outperforms convolution-based architectures in terms of accuracy, while im…
HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution
In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to…
Image Super-ResolutionSuper-ResolutionCFAT: Unleashing TriangularWindows for Image Super-resolution
Transformer-based models have revolutionized the field of image super-resolution (SR) by harnessing their inherent ability to capture complex contextual features. The overlapping rectangular shifted window technique used…
Image Super-ResolutionSuper-ResolutionCFAT: Unleashing Triangular Windows for Image Super-resolution
Transformer-based models have revolutionized the field of image super-resolution (SR) by harnessing their inherent ability to capture complex contextual features. The overlapping rectangular shifted window technique …
Image Super-ResolutionSuper-ResolutionSWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
3D object detection in point clouds is a core component for modern robotics and autonomous driving systems. A key challenge in 3D object detection comes from the inherent sparse nature of point occupancy within the 3D sc…
3D Object DetectionAutonomous DrivingObjectobject-detection+1