Unified Transformer Tracker for Object Tracking

TL;DR

The paper introduces a Unified Transformer Tracker (UTT) that effectively handles both Single Object Tracking and Multiple Object Tracking within a single framework, leveraging large-scale datasets for improved performance.

Contribution

It proposes a novel unified transformer-based model that can be trained jointly on SOT and MOT datasets, unifying tracking tasks in a single paradigm.

Findings

Achieves competitive results on multiple benchmarks.

Effectively trains on combined SOT and MOT datasets.

Demonstrates versatility in different tracking scenarios.

Abstract

As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not easily adapted to the other due to the divergent training datasets and tracking objects of both tasks. Although UniTrack \cite{wang2021different} demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single object tracking. In this work, we present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both SOT and MOT. The correlation between the target and tracking frame features is exploited to localize the target. We demonstrate that both SOT and MOT tasks can be solved within this framework. The model can be simultaneously end-to-end trained by alternatively optimizing the SOT and MOT objectives on the datasets of individual tasks. Extensive experiments are conducted on several benchmarks with a unified model trained on SOT and MOT datasets. Code will be available at https://github.com/Flowerfan/Trackron.