Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Pengcheng, Bai, Xiao, Zheng, Jin, Ning, Xin
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2309.04967
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910360223612928
author Zhang, Pengcheng
Bai, Xiao
Zheng, Jin
Ning, Xin
author_facet Zhang, Pengcheng
Bai, Xiao
Zheng, Jin
Ning, Xin
contents End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for persons earch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04967
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Fully Decoupled End-to-End Person Search
Zhang, Pengcheng
Bai, Xiao
Zheng, Jin
Ning, Xin
Computer Vision and Pattern Recognition
End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search performance. In this paper, we propose to fully decouple person search towards optimal person search. A task-incremental person search network is proposed to incrementally construct an end-to-end model for the detection and re-id sub-task, which decouples the model architecture for the two sub-tasks. The proposed task-incremental network allows task-incremental training for the two conflicting tasks. This enables independent learning for different objectives thus fully decoupled the model for persons earch. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed fully decoupled models for end-to-end person search.
title Towards Fully Decoupled End-to-End Person Search
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.04967