Abstract
Person re-identification (ReID) models are known to suffer from camera bias, where learned representations cluster according to camera viewpoints rather than identity, leading to significant performance degradation under (inter-camera) domain shifts in real-world surveillance systems when new cameras are added to camera networks. State-of-the-art test-time adaptation (TTA) methods, largely designed for classification tasks, rely on classification entropy-based objectives that fail to generalize well to ReID, thus making them unsuitable for tackling camera bias. In this paper, we introduce DART$^3$, a TTA framework specifically designed to mitigate camera-induced domain shifts in person ReID. DART$^3$ (Distance-Aware Retrieval Tuning at Test Time) leverages a distance-based objective that aligns better with image retrieval tasks like ReID by exploiting the correlation between nearest-neighbor distance and prediction error. Unlike prior ReID-specific domain adaptation methods, DART$^3$ requires no source data, architectural modifications, or retraining, and can be deployed in both fully black-box and hybrid settings. Empirical evaluations on multiple ReID benchmarks indicate that DART$^3$ and DART$^3$ LITE, a lightweight alternative to the approach, consistently outperforms state-of-the-art TTA baselines, making for a viable option to online learning to mitigate the adverse effects of camera bias.
Abstract (translated)
人员重新识别（ReID）模型在面对摄像机偏差时会表现不佳，这种情况下，学习到的表示方式根据摄像机视角进行聚类，而不是按身份分组。这导致了当现实世界的监控系统中加入新的摄像头（跨摄像机领域转移）时，性能显著下降。现有的测试时间适应（TTA, Test-Time Adaptation）方法主要是为分类任务设计的，依赖于基于分类熵的目标函数，这些目标函数无法很好地推广到ReID任务上，因此不适合解决摄像机偏差问题。 在本文中，我们提出了DART$^3$，这是一种专门用于缓解人员重新识别中的相机引起的领域偏移的测试时间适应框架。DART$^3$（Distance-Aware Retrieval Tuning at Test Time）采用了一个基于距离的目标函数，该目标函数更适合于像ReID这样的图像检索任务，它通过利用最近邻距离和预测误差之间的相关性来实现这一点。 与以前专门针对ReID领域的领域适应方法不同，DART$^3$不需要源数据、架构修改或重新训练，并且可以在全黑盒和混合设置中部署。在多个ReID基准测试上的实证评估表明，DART$^3$及其轻量级变体DART$^3$ LITE始终优于现有的TTA基线方法，这使得它成为缓解摄像机偏差不良影响的在线学习的一种可行选择。
URL
https://arxiv.org/abs/2505.18337
