Towards Grand Unification of Object Tracking
This work addresses the problem of overspecialization in object tracking for researchers and practitioners, offering a more generalizable approach, though it is incremental in unifying existing tasks rather than introducing a new paradigm.
The authors tackled the fragmented nature of object tracking by proposing Unicorn, a unified method that solves four tracking tasks (SOT, MOT, VOS, MOTS) with a single network and parameters, achieving performance on-par or better than task-specific models across 8 datasets.
We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters. Due to the fragmented definitions of the object tracking problem itself, most existing trackers are developed to address a single or part of tasks and overspecialize on the characteristics of specific tasks. By contrast, Unicorn provides a unified solution, adopting the same input, backbone, embedding, and head across all tracking tasks. For the first time, we accomplish the great unification of the tracking network architecture and learning paradigm. Unicorn performs on-par or better than its task-specific counterparts in 8 tracking datasets, including LaSOT, TrackingNet, MOT17, BDD100K, DAVIS16-17, MOTS20, and BDD100K MOTS. We believe that Unicorn will serve as a solid step towards the general vision model. Code is available at https://github.com/MasterBin-IIAU/Unicorn.