Walker：通过在时序外观图上游走进行自监督多目标跟踪
Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs
AI总结：
提出首个自监督多目标跟踪器Walker，通过设计准密集时序外观图并优化随机游走学习实例相似性，在大幅减少标注需求下于多个基准上取得竞争力性能。
摘要：
最先进的多目标跟踪（MOT）方法的监督需要巨大的标注工作量，为所有视频的所有帧提供边界框，以及实例 ID 以在时间上关联它们。为此，我们引入了 Walker，这是第一个从带有稀疏边界框标注且无跟踪标签的视频中学习的自监督跟踪器。首先，我们设计了一个准密集的时序目标外观图，并提出了一种新颖的多正例对比目标，以优化图上的随机游走并学习实例相似性。然后，我们引入一种算法来强制执行图中实例之间的互斥连接属性，从而优化为 MOT 学习到的拓扑结构。在推理时，我们提出在运动约束的双向游走下，基于最大似然转移状态将检测到的实例关联到轨迹片段。Walker 是第一个在 MOT17、DanceTrack 和 BDD100K 上实现具有竞争力性能的自监督跟踪器。值得注意的是，即使将标注需求大幅减少多达 400 倍，我们的方法也优于以前的自监督跟踪器。
英文摘要：
The supervision of state-of-the-art multiple object tracking (MOT) methods requires enormous annotation efforts to provide bounding boxes for all frames of all videos, and instance IDs to associate them through time. To this end, we introduce Walker, the first self-supervised tracker that learns from videos with sparse bounding box annotations, and no tracking labels. First, we design a quasi-dense temporal object appearance graph, and propose a novel multi-positive contrastive objective to optimize random walks on the graph and learn instance similarities. Then, we introduce an algorithm to enforce mutually-exclusive connective properties across instances in the graph, optimizing the learned topology for MOT. At inference time, we propose to associate detected instances to tracklets based on the max-likelihood transition state under motion-constrained bi-directional walks. Walker is the first self-supervised tracker to achieve competitive performance on MOT17, DanceTrack, and BDD100K. Remarkably, our proposal outperforms the previous self-supervised trackers even when drastically reducing the annotation requirements by up to 400x.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
