TrackingMiM: Efficient Mamba-in-Mamba Serialization for Real-time UAV Object Tracking
This work solves real-time processing challenges for UAV tracking systems, representing an incremental improvement over existing Mamba-based methods.
The paper tackled the problem of quadratic complexity in Vision Transformers for real-time UAV object tracking by proposing TrackingMiM, a Mamba-in-Mamba architecture that addresses temporal inconsistency, achieving state-of-the-art precision and higher speed on five benchmarks.
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.