Towards Generalizable Multi-Object Tracking

TL;DR

This paper introduces GeneralTrack, a novel multi-object tracking framework that enhances generalizability across diverse scenarios by utilizing a point-wise to instance-wise relation approach, achieving state-of-the-art results.

Contribution

The paper proposes a new relation framework for MOT that eliminates the need for balancing motion and appearance, improving cross-scenario generalization.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Demonstrates strong domain generalization capabilities.

Introduces scenario attributes to guide tracker design.

Abstract

Multi-Object Tracking MOT encompasses various tracking scenarios, each characterized by unique traits. Effective trackers should demonstrate a high degree of generalizability across diverse scenarios. However, existing trackers struggle to accommodate all aspects or necessitate hypothesis and experimentation to customize the association information motion and or appearance for a given scenario, leading to narrowly tailored solutions with limited generalizability. In this paper, we investigate the factors that influence trackers generalization to different scenarios and concretize them into a set of tracking scenario attributes to guide the design of more generalizable trackers. Furthermore, we propose a point-wise to instance-wise relation framework for MOT, i.e., GeneralTrack, which can generalize across diverse scenarios while eliminating the need to balance motion and appearance. Thanks to its superior generalizability, our proposed GeneralTrack achieves state-of-the-art performance on multiple benchmarks and demonstrates the potential for domain generalization. https://github.com/qinzheng2000/GeneralTrack.git