Sequential End-to-end Network for Efficient Person Search

TL;DR

This paper introduces SeqNet, a sequential end-to-end network for person search that improves feature quality by separating detection and re-ID tasks, and employs a context-aware matching algorithm, achieving state-of-the-art results efficiently.

Contribution

The paper proposes a novel sequential framework for person search and a context bipartite graph matching algorithm, enhancing feature quality and matching accuracy over existing parallel methods.

Findings

Achieves state-of-the-art performance on CUHK-SYSU and PRW benchmarks.

Runs at 11.5 fps on a single GPU, demonstrating efficiency.

Effectively employs context information for improved person matching.

Abstract

Person search aims at jointly solving Person Detection and Person Re-identification (re-ID). Existing works have designed end-to-end networks based on Faster R-CNN. However, due to the parallel structure of Faster R-CNN, the extracted features come from the low-quality proposals generated by the Region Proposal Network, rather than the detected high-quality bounding boxes. Person search is a fine-grained task and such inferior features will significantly reduce re-ID performance. To address this issue, we propose a Sequential End-to-end Network (SeqNet) to extract superior features. In SeqNet, detection and re-ID are considered as a progressive process and tackled with two sub-networks sequentially. In addition, we design a robust Context Bipartite Graph Matching (CBGM) algorithm to effectively employ context information as an important complementary cue for person matching. Extensive experiments on two widely used person search benchmarks, CUHK-SYSU and PRW, have shown that our method achieves state-of-the-art results. Also, our model runs at 11.5 fps on a single GPU and can be integrated into the existing end-to-end framework easily.