Abstract
Person search aims to jointly perform person detection and re-identification by localizing and identifying a query person within a gallery of uncropped scene images. Existing methods predominantly utilize ImageNet pre-trained backbones, which may be suboptimal for capturing the complex spatial context and fine-grained identity cues necessary for person search. Moreover, they rely on a shared backbone feature for both person detection and re-identification, leading to suboptimal features due to conflicting optimization objectives. In this paper, we propose DiffPS (Diffusion Prior Knowledge for Person Search), a novel framework that leverages a pre-trained diffusion model while eliminating the optimization conflict between two sub-tasks. We analyze key properties of diffusion priors and propose three specialized modules: (i) Diffusion-Guided Region Proposal Network (DGRPN) for enhanced person localization, (ii) Multi-Scale Frequency Refinement Network (MSFRN) to mitigate shape bias, and (iii) Semantic-Adaptive Feature Aggregation Network (SFAN) to leverage text-aligned diffusion features. DiffPS sets a new state-of-the-art on CUHK-SYSU and PRW.
Abstract (translated)
人搜索的目标是在一组未裁剪的场景图像中定位和识别查询人物，从而同时执行人员检测和重识别。现有方法主要使用基于ImageNet预训练的基础模型，这可能对于捕捉复杂的空间上下文和细微的身份线索以进行人员搜索而言不是最佳选择。此外，它们依赖于一个共享的基础特征用于人员检测和重识别任务，导致由于两个子任务的优化目标相互冲突而导致次优特征。 在本文中，我们提出了一种新的框架DiffPS（用于人员搜索的扩散先验知识），该框架利用预训练的扩散模型同时消除两个子任务之间的优化冲突。我们分析了扩散先验的关键属性，并提出了三个专门模块：(i) 弥漫引导区域提案网络 (DGRPN)，用于增强人物定位；(ii) 多尺度频率细化网络（MSFRN），以减轻形状偏差；以及(iii) 语义自适应特征聚合网络(SFAN)，利用与文本对齐的扩散特性。DiffPS在CUHK-SYSU和PRW数据集上达到了新的最先进水平。
URL
https://arxiv.org/abs/2510.01841
