Parameter Hierarchical Optimization for Visible-Infrared Person Re-Identification

arXiv:2404.07930v1 Announce Type: new
Abstract: Visible-infrared person re-identification (VI-reID) aims at matching cross-modality pedestrian images captured by disjoint visible or infrared cameras. Existing methods alleviate the cross-modality discrepancies via designing different kinds of network architectures. Different from available methods, in this paper, we propose a novel parameter optimizing paradigm, parameter hierarchical optimization (PHO) method, for the task of VI-ReID. It allows part of parameters to be directly optimized without any training, which narrows the search space of parameters and makes …

abstract architectures arxiv cameras cs.ai cs.cv designing hierarchical identification images network novel optimization paper paradigm pedestrian person type via