FEAR: Fast, Efficient, Accurate and Robust Visual Tracker

TL;DR

FEAR introduces a family of Siamese visual trackers that are fast, efficient, and accurate, leveraging dual-template representation and novel modules to outperform existing methods on benchmarks while also considering energy consumption.

Contribution

The paper proposes a new dual-template representation and pixel-wise fusion block, significantly improving the speed and accuracy of Siamese trackers, and introduces the FEAR benchmark for energy efficiency evaluation.

Findings

FEAR trackers outperform most Siamese trackers in accuracy and efficiency.

FEAR-XS is over 10 times faster than current Siamese trackers with near state-of-the-art accuracy.

FEAR-XS is 2.4x smaller and 4.3x faster than LightTrack, with superior accuracy.

Abstract

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.