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

TL;DR

PSDiff introduces a diffusion-based person search framework that iteratively refines detection and ReID tasks collaboratively, surpassing existing methods in accuracy with fewer parameters.

Contribution

The paper proposes a novel diffusion model for person search that abandons prior pedestrian candidates and employs a collaborative denoising layer for joint optimization.

Findings

Achieves state-of-the-art performance on standard benchmarks.

Reduces parameters and computational overhead compared to previous methods.

Effectively integrates detection and ReID through iterative collaborative refinement.

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. 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.