Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers
This addresses the problem of tracking objects in videos without labeled data, which is incremental as it adapts existing diffusion models to a new task.
The paper tackles unsupervised visual tracking by leveraging a pre-trained text-to-image diffusion model, achieving state-of-the-art performance on five benchmark datasets.
We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained diffusion model, such as the understanding of image semantics and structural information, to address unsupervised visual tracking. To this end, we design an initial prompt learner to enable the diffusion model to recognize the tracking target by learning a prompt representing the target. Furthermore, to facilitate dynamic adaptation of the prompt to the target's movements, we propose an online prompt updater. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our proposed method, which also achieves state-of-the-art performance.