Person Search via A Mask-Guided Two-Stream CNN Model

TL;DR

This paper introduces a mask-guided two-stream CNN model for person search, improving person re-identification by separately modeling foreground and original image features, leading to state-of-the-art results.

Contribution

It proposes a novel two-stream CNN approach that segments foreground persons for enhanced feature extraction in person search tasks.

Findings

Achieved 83.0% mAP on CUHK-SYSU benchmark.

Achieved 32.6% mAP on PRW benchmark.

Surpassed previous state-of-the-art performance by over 5 percentage points.

Abstract

In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification~(re-ID). Instead of sharing representations in a single joint model, we find that separating detector and re-ID feature extraction yields better performance. In order to extract more representative features for each identity, we segment out the foreground person from the original image patch. We propose a simple yet effective re-ID method, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams. From the experiments on two standard person search benchmarks of CUHK-SYSU and PRW, we achieve mAP of $83.0\%$ and $32.6\%$ respectively, surpassing the state of the art by a large margin (more than 5pp).