SiamMask: A Framework for Fast Online Object Tracking and Segmentation
This work addresses the need for efficient and unified frameworks for real-time object tracking and segmentation in computer vision applications, offering a practical solution with incremental improvements over existing Siamese approaches.
The paper tackles the problem of performing both visual object tracking and video object segmentation in real-time with a single method, achieving high processing efficiency at around 55 frames per second and delivering state-of-the-art results on tracking benchmarks with competitive segmentation performance.
In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the offline training procedure of popular fully-convolutional Siamese approaches by augmenting their losses with a binary segmentation task. Once the offline training is completed, SiamMask only requires a single bounding box for initialization and can simultaneously carry out visual object tracking and segmentation at high frame-rates. Moreover, we show that it is possible to extend the framework to handle multiple object tracking and segmentation by simply re-using the multi-task model in a cascaded fashion. Experimental results show that our approach has high processing efficiency, at around 55 frames per second. It yields real-time state-of-the-art results on visual-object tracking benchmarks, while at the same time demonstrating competitive performance at a high speed for video object segmentation benchmarks.