FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
This work addresses the need for fast and efficient visual tracking, particularly for mobile devices, by offering incremental improvements in speed and energy efficiency over existing Siamese trackers.
The authors tackled the problem of improving speed and efficiency in Siamese visual trackers by introducing FEAR, a family of trackers that use dual-template representation and pixel-wise fusion, achieving over 10 times faster tracking with near state-of-the-art accuracy and superior performance in benchmarks.
We present FEAR, a family of fast, efficient, accurate, and robust Siamese visual trackers. We present a novel and efficient way to benefit from dual-template representation for object model adaption, which incorporates temporal information with only a single learnable parameter. We further improve the tracker architecture with a pixel-wise fusion block. By plugging-in sophisticated backbones with the abovementioned modules, FEAR-M and FEAR-L trackers surpass most Siamese trackers on several academic benchmarks in both accuracy and efficiency. Employed with the lightweight backbone, the optimized version FEAR-XS offers more than 10 times faster tracking than current Siamese trackers while maintaining near state-of-the-art results. FEAR-XS tracker is 2.4x smaller and 4.3x faster than LightTrack with superior accuracy. In addition, we expand the definition of the model efficiency by introducing FEAR benchmark that assesses energy consumption and execution speed. We show that energy consumption is a limiting factor for trackers on mobile devices. Source code, pretrained models, and evaluation protocol are available at https://github.com/PinataFarms/FEARTracker.