Abstract
Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in appearance, motion pattern, and catagory between the training and testing data, model performance degrades considerably during online inference in MOT. Test-Time Adaptation (TTA) has emerged as a promising paradigm to alleviate such distribution shifts. However, existing TTA methods often fail to deliver satisfactory results in MOT, as they primarily focus solely on frame-level adaptation while neglecting temporal consistency and identity association across frames and videos. Inspired by human decision-making process, this paper propose a Test-time Calibration from Experience and Intuition (TCEI) framework. In this framework, the Intuitive system utilizes transient memory to recall recently observed objects for rapid predictions, while the Experiential system leverages the accumulated experience from prior test videos to reassess and calibrate these intuitive predictions. Furthermore, both confident and uncertain objects during online testing are exploited as historical priors and reflective cases, respectively, enabling the model to adapt to the testing environment and alleviate performance degradation. Extensive experiments demonstrate that the proposed TCEI framework consistently achieves superior performance across multiple benchmark datasets and significantly enhances the model's adaptability under distribution shifts. The code will be released at this https URL.
Abstract (translated)
多目标跟踪（MOT）长期以来一直是计算机视觉领域的基础任务，在众多现实场景中有着广泛应用。然而，由于训练数据与测试数据在外观、运动模式和类别上存在分布偏移，MOT模型的在线推理性能会显著下降。测试时适应（TTA）作为一种有前景的范式，能够有效缓解此类分布偏移问题。但现有TTA方法在MOT任务中往往难以取得满意效果，主要因为它们仅关注帧级适应，而忽视了跨帧与跨视频间的时间一致性与身份关联。受人类决策过程启发，本文提出了一种基于经验与直觉的测试时校准（TCEI）框架。该框架中，直觉系统利用短暂记忆回忆近期观测目标以实现快速预测，而经验系统则借助先前测试视频积累的经验对直觉预测进行重新评估与校准。此外，在线测试中同时利用高置信度与低置信度目标，分别作为历史先验与反思案例，使模型能够适应测试环境并缓解性能下降。大量实验表明，所提出的TCEI框架在多个基准数据集上持续取得优越性能，并显著增强了模型在分布偏移下的适应性。代码将在以下网址发布：https://URL。
URL
https://arxiv.org/abs/2603.21629
