LEAPS: End-to-End One-Step Person Search With Learnable Proposals

TL;DR

LEAPS introduces an end-to-end person search method with learnable proposals, enabling direct detection and re-identification without post-processing, achieving state-of-the-art accuracy and speed on benchmark datasets.

Contribution

The paper presents a novel end-to-end person search framework with learnable proposals and a dynamic re-id head, improving accuracy and efficiency over existing methods.

Findings

Achieves 55.0% mAP on CUHK-SYSU, outperforming previous methods by 1.7%.

Provides around two-fold speedup on PRW dataset.

Eliminates the need for non-maximum suppression in person search.

Abstract

We propose an end-to-end one-step person search approach with learnable proposals, named LEAPS. Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing. The dynamic person search head comprises a detection head and a novel flexible re-id head. Our flexible re-id head first employs a dynamic region-of-interest (RoI) operation to extract discriminative RoI features of the proposals. Then, it generates re-id features using a plain and a hierarchical interaction re-id module. To better guide discriminative re-id feature learning, we introduce a diverse re-id sample matching strategy, instead of bipartite matching in detection head. Comprehensive experiments reveal the benefit of the proposed LEAPS, achieving a favorable performance on two public person search benchmarks: CUHK-SYSU and PRW. When using the same ResNet50 backbone, our LEAPS obtains a mAP score of 55.0%, outperforming the best reported results in literature by 1.7%, while achieving around a two-fold speedup on the challenging PRW dataset. Our source code and models will be released.