论文标题
迈向物体跟踪的大统一
Towards Grand Unification of Object Tracking
论文作者
论文摘要
我们提出了一种称为独角兽的统一方法，可以使用相同的模型参数同时使用单个网络解决四个跟踪问题（SOT，MOT，VOS，MOTS）。由于对象跟踪问题本身的定义零散，因此开发了大多数现有的跟踪器来解决任务的单个或一部分，并过度专业化特定任务的特征。相比之下，Unicorn提供了一个统一的解决方案，在所有跟踪任务中采用相同的输入，骨干，嵌入和头部。我们第一次完成了跟踪网络体系结构和学习范式的巨大统一。独角兽在8个跟踪数据集中的表现出色或比其特定于任务的对应物更好，包括Lasot，Trackingnet，Mot17，BDD100K，Davis16-17，MOTS20和BDD100K MOT。我们认为，独角兽将是朝着一般视觉模型迈出的坚实一步。代码可从https://github.com/masterbin-iiau/unicorn获得。
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.
