Unsupervised Green Object Tracker (GOT) without Offline Pre-training

TL;DR

This paper introduces GOT, an unsupervised, lightweight, and transparent single object tracker that achieves competitive accuracy without offline pre-training, suitable for edge devices.

Contribution

GOT is a novel ensemble-based unsupervised tracker with a tiny model and low computational cost, eliminating the need for offline pre-training.

Findings

Achieves competitive accuracy with state-of-the-art unsupervised trackers.

Has a model size of less than 3,000 parameters.

Requires around 58 million FLOPs per frame, suitable for mobile deployment.

Abstract

Supervised trackers trained on labeled data dominate the single object tracking field for superior tracking accuracy. The labeling cost and the huge computational complexity hinder their applications on edge devices. Unsupervised learning methods have also been investigated to reduce the labeling cost but their complexity remains high. Aiming at lightweight high-performance tracking, feasibility without offline pre-training, and algorithmic transparency, we propose a new single object tracking method, called the green object tracker (GOT), in this work. GOT conducts an ensemble of three prediction branches for robust box tracking: 1) a global object-based correlator to predict the object location roughly, 2) a local patch-based correlator to build temporal correlations of small spatial units, and 3) a superpixel-based segmentator to exploit the spatial information of the target frame. GOT offers competitive tracking accuracy with state-of-the-art unsupervised trackers, which demand heavy offline pre-training, at a lower computation cost. GOT has a tiny model size (<3k parameters) and low inference complexity (around 58M FLOPs per frame). Since its inference complexity is between 0.1%-10% of DL trackers, it can be easily deployed on mobile and edge devices.