Domain generalized person reidentification based on skewness regularity of higher-order statistics

Simple item page
dc.contributor.authorXiong, Mingfu
dc.contributor.authorXu, Yang
dc.contributor.authorHu, Ruimin
dc.contributor.authorWang, Zhongyuan
dc.contributor.authorDel Ser, Javier
dc.contributor.authorMuhammad, Khan
dc.contributor.authorXiong, Zixiang
dc.contributor.institutionIA
dc.date.accessioned2024-09-06T09:25:02Z
dc.date.available2024-09-06T09:25:02Z
dc.date.issued2024-10-09
dc.descriptionPublisher Copyright: © 2024 Elsevier B.V.
dc.description.abstractThe goal of domain-generalized person reidentification (DG-ReID) is to train a model in the source domain and apply it directly to unknown target domains for specific pedestrian retrieval. Existing methods rely primarily on low-order statistics (such as the mean, standard deviation, or variance), thereby ensuring the stability of the source domain data distribution for model training. However, such methods underperform when the data follow a non-Gaussian distribution, thereby reducing the generalization ability of the model on unseen target domains. To address this issue, this study proposes an instance normalization-based skewness regularity (INSR) framework that uses high-order statistics (skewness and high-order moments) to measure the skewness and regularity of the data distribution. Such measures allow further learning of the morphological features (skewness degree, trait of data near the mean, etc.) of complex data distributions for DG-ReID. Specifically, the proposed framework first extracts the skewness and third-order moments from the source domains, which provide more features (high-order moments, variance, etc.) to characterize the data distribution. Subsequently, a batch normalization-like operation was implemented to project the data into a new feature space with zero mean and unit variance, enhancing model adaption and accuracy. Extensive experiments were conducted on small-scale (VIPeR, PRID, GRID, and i-LIDS) and large-scale (Market-1501, DukeMTMC-reID, CUHK03, MSMT17) public datasets using two different protocols, demonstrating that the proposed INSR framework significantly outperforms other state-of-the-art counterparts for DG-ReID.en
dc.description.statusPeer reviewed
dc.identifier.citationXiong , M , Xu , Y , Hu , R , Wang , Z , Del Ser , J , Muhammad , K & Xiong , Z 2024 , ' Domain generalized person reidentification based on skewness regularity of higher-order statistics ' , Knowledge-Based Systems , vol. 301 , 112206 . https://doi.org/10.1016/j.knosys.2024.112206
dc.identifier.doi10.1016/j.knosys.2024.112206
dc.identifier.issn0950-7051
dc.identifier.urihttps://hdl.handle.net/11556/4826
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85200261024&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofKnowledge-Based Systems
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsDomain generalization
dc.subject.keywordsHigher-order statistics
dc.subject.keywordsPerson reidentification
dc.subject.keywordsSkewness regularity
dc.subject.keywordsVideo surveillance
dc.subject.keywordsSoftware
dc.subject.keywordsManagement Information Systems
dc.subject.keywordsInformation Systems and Management
dc.subject.keywordsArtificial Intelligence
dc.titleDomain generalized person reidentification based on skewness regularity of higher-order statisticsen
dc.typejournal article
Files