Leveraging Prior Knowledge of Diffusion Model for Person Search

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Giyeol, Yang, Sooyoung, Oh, Jihyong, Kang, Myungjoo, Eom, Chanho
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915530731945984
author Kim, Giyeol
Yang, Sooyoung
Oh, Jihyong
Kang, Myungjoo
Eom, Chanho
author_facet Kim, Giyeol
Yang, Sooyoung
Oh, Jihyong
Kang, Myungjoo
Eom, Chanho
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01841
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Prior Knowledge of Diffusion Model for Person Search
Kim, Giyeol
Yang, Sooyoung
Oh, Jihyong
Kang, Myungjoo
Eom, Chanho
Computer Vision and Pattern Recognition
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.
title Leveraging Prior Knowledge of Diffusion Model for Person Search
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.01841