dc.contributor.author | Li, W | |
dc.contributor.author | Gong, S | |
dc.contributor.author | Zhu, X | |
dc.date.accessioned | 2021-06-24T10:10:14Z | |
dc.date.available | 2021-06-24T10:10:14Z | |
dc.date.issued | 2021-06 | |
dc.identifier.issn | 0031-3203 | |
dc.identifier.other | ARTN 107862 | |
dc.identifier.other | ARTN 107862 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/72703 | |
dc.description.abstract | Existing person search methods typically focus on improving person detection accuracy. This ignores the model inference efficiency, which however is fundamentally significant for real-world applications. In this work, we address this limitation by investigating the scalability problem of person search involving both model accuracy and inference efficiency simultaneously. Specifically, we formulate a Hierarchical Distillation Learning (HDL) approach. With HDL, we aim to comprehensively distil the knowledge of a strong teacher model with strong learning capability to a lightweight student model with weak learning capability. To facilitate the HDL process, we design a simple and powerful teacher model for joint learning of person detection and person re-identification matching in unconstrained scene images. Extensive experiments show the modelling advantages and cost-effectiveness superiority of HDL over the state-of-the-art person search methods on three large person search benchmarks: CUHK-SYSU, PRW, and DukeMTMC-PS. | en_US |
dc.publisher | Elsevier | en_US |
dc.relation.ispartof | PATTERN RECOGNITION | |
dc.rights | https://doi.org/10.1016/j.patcog.2021.107862 | |
dc.subject | Person search | en_US |
dc.subject | Person re-identification | en_US |
dc.subject | Person detection | en_US |
dc.subject | Knowledge distillation | en_US |
dc.subject | Scalability | en_US |
dc.subject | Model inference efficiency | en_US |
dc.title | Hierarchical distillation learning for scalable person search | en_US |
dc.type | Article | en_US |
dc.rights.holder | © 2021 Elsevier Ltd. | |
dc.identifier.doi | 10.1016/j.patcog.2021.107862 | |
pubs.author-url | http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000632385300002&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=612ae0d773dcbdba3046f6df545e9f6a | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Accepted | en_US |
pubs.volume | 114 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |