mustansarfiaz / ps-arm Goto Github PK

Abstract. 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, previous study focuses on rich feature information learning, it’s still hard to re- trieve 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 per- son 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 intro- ducing 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 supervisions 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: CUHK-SYSU [1] and PRW [2]. 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

Home Page: https://openaccess.thecvf.com/content/ACCV2022/papers/Fiaz_PS-ARM_An_End-to-End_Attention-aware_Relation_Mixer_Network_for_Person_Search_ACCV_2022_paper.pdf

License: MIT License