PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search

by   Mustansar Fiaz, et al.

Person search is a challenging problem with various real-world applications, that aims at joint person detection and re-identification of a query person from uncropped gallery images. Although, the previous study focuses on rich feature information learning, it is still hard to retrieve the query person due to the occurrence of appearance deformations and background distractors. In this paper, we propose a novel attention-aware relation mixer (ARM) module for person search, which exploits the global relation between different local regions within RoI of a person and make it robust against various appearance deformations and occlusion. The proposed ARM is composed of a relation mixer block and a spatio-channel attention layer. The relation mixer block introduces a spatially attended spatial mixing and a channel-wise attended channel mixing for effectively capturing discriminative relation features within an RoI. These discriminative relation features are further enriched by introducing a spatio-channel attention where the foreground and background discriminability is empowered in a joint spatio-channel space. Our ARM module is generic and it does not rely on fine-grained supervision or topological assumptions, hence being easily integrated into any Faster R-CNN based person search methods. Comprehensive experiments are performed on two challenging benchmark datasets: CUHKSYSU and PRW. Our PS-ARM achieves state-of-the-art performance on both datasets. On the challenging PRW dataset, our PS-ARM achieves an absolute gain of 5 in the mAP score over SeqNet, while operating at a comparable speed.


page 3

page 11

page 12


Sequential Transformer for End-to-End Person Search

Person Search aims to simultaneously localize and recognize a target per...

Learning Context Graph for Person Search

Person re-identification has achieved great progress with deep convoluti...

Attention Driven Person Re-identification

Person re-identification (ReID) is a challenging task due to arbitrary h...

Query-guided End-to-End Person Search

Person search has recently gained attention as the novel task of finding...

Person Search Challenges and Solutions: A Survey

Person search has drawn increasing attention due to its real-world appli...

Neural Person Search Machines

We investigate the problem of person search in the wild in this work. In...

Cascade Transformers for End-to-End Person Search

The goal of person search is to localize a target person from a gallery ...

Please sign up or login with your details

Forgot password? Click here to reset