关联所有检测到的目标：推动检测跟踪范式向未知类别拓展
Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown
AI总结：
针对闭词汇与开词汇多目标跟踪方法难以兼顾两类任务的问题，提出统一框架AED，通过相似度解码器和以关联为中心的学习机制，无需先验知识即可在多个基准上取得更优性能。
摘要：
多目标跟踪（MOT）是计算机视觉领域中一个关键且极具前景的分支。经典的闭词汇多目标跟踪（CV-MOT）方法旨在跟踪预定义类别的目标。近年来，一些开词汇多目标跟踪（OV-MOT）方法成功解决了未知类别跟踪的问题，但我们发现CV-MOT和OV-MOT方法各自都难以在对方的任务中表现出色。本文提出了一个统一框架Associate Everything Detected（AED，关联所有检测目标），该框架可与任意现成检测器集成，同时处理CV-MOT和OV-MOT任务，且支持未知类别。与现有基于检测的跟踪MOT方法不同，AED无需依赖先验知识（如运动线索），仅依靠高鲁棒性的特征学习来处理OV-MOT任务中的复杂轨迹，同时在CV-MOT任务中保持优异性能。具体而言，我们将关联任务建模为相似度解码问题，并提出了带有以关联为中心学习机制的sim-decoder（相似度解码器）。sim-decoder从空间、时间和跨片段三个维度计算相似度，随后以关联为中心的学习机制利用这三重相似度，确保提取的特征适用于连续跟踪，且具备足够的鲁棒性以泛化到未知类别。与现有性能强劲的OV-MOT和CV-MOT方法相比，AED在无需任何先验知识的情况下，在TAO、SportsMOT和DanceTrack数据集上取得了更优的性能。我们的代码可在https://github.com/balabooooo/AED获取。
英文摘要：
Multi-object tracking (MOT) emerges as a pivotal and highly promising branch in the field of computer vision. Classical closed-vocabulary MOT (CV-MOT) methods aim to track objects of predefined categories. Recently, some open-vocabulary MOT (OV-MOT) methods have successfully addressed the problem of tracking unknown categories. However, we found that the CV-MOT and OV-MOT methods each struggle to excel in the tasks of the other. In this paper, we present a unified framework, Associate Everything Detected (AED), that simultaneously tackles CV-MOT and OV-MOT by integrating with any off-the-shelf detector and supports unknown categories. Different from existing tracking-by-detection MOT methods, AED gets rid of prior knowledge (e.g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories in OV-MOT tasks while keeping excellent performance in CV-MOT tasks. Specifically, we model the association task as a similarity decoding problem and propose a sim-decoder with an association-centric learning mechanism. The sim-decoder calculates similarities in three aspects: spatial, temporal, and cross-clip. Subsequently, association-centric learning leverages these threefold similarities to ensure that the extracted features are appropriate for continuous tracking and robust enough to generalize to unknown categories. Compared with existing powerful OV-MOT and CV-MOT methods, AED achieves superior performance on TAO, SportsMOT, and DanceTrack without any prior knowledge. Our code is available at https://github.com/balabooooo/AED.
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。
