PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jia, Chengyou, Luo, Minnan, Dang, Zhuohang, Dai, Guang, Chang, Xiaojun, Wang, Jingdong
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910765260210176
author Jia, Chengyou
Luo, Minnan
Dang, Zhuohang
Dai, Guang
Chang, Xiaojun
Wang, Jingdong
author_facet Jia, Chengyou
Luo, Minnan
Dang, Zhuohang
Dai, Guang
Chang, Xiaojun
Wang, Jingdong
contents Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes two sub-tasks, \ie, pedestrian detection and Re-IDentification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11125
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
Jia, Chengyou
Luo, Minnan
Dang, Zhuohang
Dai, Guang
Chang, Xiaojun
Wang, Jingdong
Computer Vision and Pattern Recognition
Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes two sub-tasks, \ie, pedestrian detection and Re-IDentification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead.
title PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.11125