Robust Tracking via Mamba-based Context-aware Token Learning

TL;DR

The paper introduces a simple, robust tracking method that separates temporal and appearance information learning, using a mamba-based context-aware token approach to improve efficiency and accuracy in real-time tracking.

Contribution

It proposes a novel tracker that extracts temporal relations from representative tokens, reducing computational cost and interference compared to existing methods.

Findings

Achieves competitive performance on multiple benchmarks.

Operates in real-time with efficient computation.

Effectively models temporal relations with a mamba-based module.

Abstract

How to make a good trade-off between performance and computational cost is crucial for a tracker. However, current famous methods typically focus on complicated and time-consuming learning that combining temporal and appearance information by input more and more images (or features). Consequently, these methods not only increase the model's computational source and learning burden but also introduce much useless and potentially interfering information. To alleviate the above issues, we propose a simple yet robust tracker that separates temporal information learning from appearance modeling and extracts temporal relations from a set of representative tokens rather than several images (or features). Specifically, we introduce one track token for each frame to collect the target's appearance information in the backbone. Then, we design a mamba-based Temporal Module for track tokens to be aware of context by interacting with other track tokens within a sliding window. This module consists of a mamba layer with autoregressive characteristic and a cross-attention layer with strong global perception ability, ensuring sufficient interaction for track tokens to perceive the appearance changes and movement trends of the target. Finally, track tokens serve as a guidance to adjust the appearance feature for the final prediction in the head. Experiments show our method is effective and achieves competitive performance on multiple benchmarks at a real-time speed. Code and trained models will be available at https://github.com/GXNU-ZhongLab/TemTrack.