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

arXiv:2309.11125v2 Announce Type: replace
Abstract: 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. …

abstract aim arxiv challenges collaborative cs.cv current detection diffusion diffusion model face identification iterative network pedestrian person progress query search tasks type