OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning

TL;DR

OneTracker unifies various visual object tracking tasks by leveraging foundation models and efficient prompt-based tuning, achieving state-of-the-art results across multiple benchmarks.

Contribution

The paper introduces a general framework that unifies RGB and RGB+X tracking tasks using foundation models and prompt tuning, enabling efficient adaptation and superior performance.

Findings

Outperforms existing models on 11 benchmarks

Achieves state-of-the-art results across 6 tracking tasks

Demonstrates effective parameter-efficient fine-tuning

Abstract

Visual object tracking aims to localize the target object of each frame based on its initial appearance in the first frame. Depending on the input modility, tracking tasks can be divided into RGB tracking and RGB+X (e.g. RGB+N, and RGB+D) tracking. Despite the different input modalities, the core aspect of tracking is the temporal matching. Based on this common ground, we present a general framework to unify various tracking tasks, termed as OneTracker. OneTracker first performs a large-scale pre-training on a RGB tracker called Foundation Tracker. This pretraining phase equips the Foundation Tracker with a stable ability to estimate the location of the target object. Then we regard other modality information as prompt and build Prompt Tracker upon Foundation Tracker. Through freezing the Foundation Tracker and only adjusting some additional trainable parameters, Prompt Tracker inhibits the strong localization ability from Foundation Tracker and achieves parameter-efficient finetuning on downstream RGB+X tracking tasks. To evaluate the effectiveness of our general framework OneTracker, which is consisted of Foundation Tracker and Prompt Tracker, we conduct extensive experiments on 6 popular tracking tasks across 11 benchmarks and our OneTracker outperforms other models and achieves state-of-the-art performance.