PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
This addresses the problem of improving accuracy and efficiency in person search for applications like surveillance, though it appears incremental as it builds on existing diffusion models.
The paper tackles the suboptimal pedestrian candidates and lack of collaboration between detection and Re-ID tasks in person search by proposing PSDiff, a diffusion-based framework that formulates it as a dual denoising process, achieving state-of-the-art performance with fewer parameters and elastic computing overhead.
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.