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.
翻译:我们提出了一个统一的方法,称为 " 独角兽 ",它可以同时用相同的模型参数解决四个跟踪问题(SOT、MOT、VOS、MOTS),使用一个单一的网络解决四个跟踪问题。由于对物体跟踪问题本身的定义零散,大多数现有跟踪器是用来处理一个或一个部分任务,并且对具体任务的特点过于专门化。相反,独角兽则提供统一的解决办法,在所有跟踪任务中采用同样的输入、主干、嵌入和头等。我们第一次实现了跟踪网络结构和学习模式的巨大统一。独角兽在8个跟踪数据集(包括LaSOT、跟踪网、MOT17、BDD100K、DAVIS16-17、MOTS20和BDD100K MATS)中,在8个跟踪数据集(包括LaSOT、跟踪网、MOT17、BDD100K、DTS20和BDD100K MOTS)中,在8个跟踪数据集中的表现优异或优于其具体任务对应的对等。我们认为独角兽。我们认为,独角兽将作为通观模型的坚实步骤。可在http://gitub.com/MasterBin-II-IIAU/U/Unicornc.