TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking

TL;DR

TrackingMiM introduces a nested Mamba-in-Mamba architecture that efficiently processes UAV image sequences, addressing temporal inconsistency and achieving state-of-the-art tracking precision with higher speed.

Contribution

It proposes a novel Mamba-in-Mamba framework that independently processes temporal and spatial information, improving real-time UAV tracking performance.

Findings

Achieves state-of-the-art accuracy on UAV benchmarks.

Offers higher processing speed compared to existing methods.

Effectively handles dense image sequences with minimal computation.

Abstract

The Vision Transformer (ViT) model has long struggled with the challenge of quadratic complexity, a limitation that becomes especially critical in unmanned aerial vehicle (UAV) tracking systems, where data must be processed in real time. In this study, we explore the recently proposed State-Space Model, Mamba, leveraging its computational efficiency and capability for long-sequence modeling to effectively process dense image sequences in tracking tasks. First, we highlight the issue of temporal inconsistency in existing Mamba-based methods, specifically the failure to account for temporal continuity in the Mamba scanning mechanism. Secondly, building upon this insight,we propose TrackingMiM, a Mamba-in-Mamba architecture, a minimal-computation burden model for handling image sequence of tracking problem. In our framework, the mamba scan is performed in a nested way while independently process temporal and spatial coherent patch tokens. While the template frame is encoded as query token and utilized for tracking in every scan. Extensive experiments conducted on five UAV tracking benchmarks confirm that the proposed TrackingMiM achieves state-of-the-art precision while offering noticeable higher speed in UAV tracking.