Cross-scale global attention feature pyramid network for person search

Person search aims to locate the target person in real unconstrained scene images. It faces many challenges such as multi-scale and fine-grained. To address the challenges, a novel cross-scale global attention feature pyramid network (CSGAFPN) is proposed. Firstly, we design a novel multi-head global attention module (MHGAM), which adopts cosine similarity and sparse query location methods to effectively capture cross-scale long-distance dependence. Then, we design the CSGAFPN, which extends top-down feature pyramid network with bottom-up connections and embeds MHGAMs to the connections. CSGAFPN can capture cross-scale long-distance global correlation from multi-scale feature maps, selectively strengthen important features and restrain less important features. CSGAFPN is applied for both person detection and person re-identification (reID) sub-tasks of person search, it can well handle the multi-scale and fine-grained challenges, and significantly improve person search performance. Furthermore, the output multi-scale feature maps of CSGAFPN are processed by an adaptive feature aggregation with attention (AFAA) layer to further improve the performance. Numerous exper-iments with two public person search datasets, CUHK-SYSU and PRW, show our CSGAFPN based approach ac-quires better performance than other state-of-the-art (SOTA) person search approaches. (c) 2021 Elsevier B.V. All rights reserved.