Robust Partial Matching for Person Search in the Wild

TL;DR

This paper introduces APNet, a novel network that refines bounding boxes to improve person re-identification by aligning and selecting discriminative body parts, enhancing robustness in real-world person search scenarios.

Contribution

The paper proposes APNet, a new approach for person search that refines bounding boxes and aligns part features, along with a large-scale challenging dataset LSPS for evaluation.

Findings

APNet significantly improves performance on LSPS dataset.

APNet achieves competitive results on CUHK-SYSU and PRW benchmarks.

The method enhances robustness to occlusions and noisy detections.

Abstract

Various factors like occlusions, backgrounds, etc., would lead to misaligned detected bounding boxes , e.g., ones covering only portions of human body. This issue is common but overlooked by previous person search works. To alleviate this issue, this paper proposes an Align-to-Part Network (APNet) for person detection and re-Identification (reID). APNet refines detected bounding boxes to cover the estimated holistic body regions, from which discriminative part features can be extracted and aligned. Aligned part features naturally formulate reID as a partial feature matching procedure, where valid part features are selected for similarity computation, while part features on occluded or noisy regions are discarded. This design enhances the robustness of person search to real-world challenges with marginal computation overhead. This paper also contributes a Large-Scale dataset for Person Search in the wild (LSPS), which is by far the largest and the most challenging dataset for person search. Experiments show that APNet brings considerable performance improvement on LSPS. Meanwhile, it achieves competitive performance on existing person search benchmarks like CUHK-SYSU and PRW.