SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking

Most current state-of-the-art trackers adopt one-stream paradigm, using a single Vision Transformer backbone for joint feature extraction and relation modeling of template and search region images. However, relation modeling between different image patches exhibits significant variations. For instance, background patches require restricted modeling participation, while foreground, particularly boundary areas, need to be emphasized. A single model may not effectively handle all kinds of relation modeling simultaneously. In this paper, we propose a novel tracker called $\textbf{SPMTrack}$ based on mixture-of-experts tailored for visual tracking task (TMoE), combining the capability of multiple experts to handle diverse relation modeling more flexibly. Benefiting from TMoE, we extend relation modeling from image pairs to spatio-temporal context, further improving tracking accuracy with minimal increase in model parameters. Moreover, we employ TMoE as a parameter-efficient fine-tuning method, substantially reducing trainable parameters, which enables us to train SPMTrack of varying scales efficiently and preserve the generalization ability of pretrained models to achieve superior performance. We conduct experiments on seven datasets, and experimental results demonstrate that our method significantly outperforms current state-of-the-art trackers. The source code will be released for further research.