计算机技术与发展2026，Vol.36Issue(6)：85-92,8.DOI:10.20165/j.cnki.ISSN1673-629X.2026.0005
基于伪深度特征自蒸馏的域泛化行人重识别
Domain Generalized Person Re-identification via Pseudo-depth Feature Self-distillation
摘要
Abstract
Depth information provides a complementary modality in person re-identification(ReID),which effectively alleviates the over-reliance on texture features and enhances the model's generalization ability in cross-domain scenarios.Motivated by the observation that local similarity facilitates learning domain-invariant representations,we propose a depth-guided self-distillation for domain generalization framework.Specifically,we leverage Depth Anything to generate pseudo depth maps as cross-domain consistency self-su-pervised signals,and design a pseudo-supervised depth feature extraction mechanism with dual-dimensional attention to enable geometry-aware representation learning.Furthermore,a cross-domain depth similarity module and an edge similarity module are introduced to achieve geometry-guided cross-domain feature disentanglement.To enhance domain invariance,we construct a dynamic memory bank to store depth,edge,and local features,and adopt a dual-domain reciprocal self-attention mechanism to mine semantic cues that are or-thogonal to identity classification through contrastive learning.Ultimately,the proposed framework transforms geometric consistency constraints into implicit regularization for the classification task,thereby improving generalization while preserving discriminative power.Extensive experiments on benchmark cross-domain datasets,including Market1501,MSMT17,CUHK-SYSU,CUHK03-NP,and RandPerson,demonstrate the effectiveness and superiority of the proposed framework.关键词
域泛化/行人重识别/自注意力/自蒸馏/对比学习Key words
domain generalizations/person re-identification/self-attention/self-distillation/contrast learning分类
信息技术与安全科学引用本文复制引用
董文永,梁智学,周孟强,唐志祥..基于伪深度特征自蒸馏的域泛化行人重识别[J].计算机技术与发展,2026,36(6):85-92,8.基金项目
国家自然基金面上项目(61672024) （61672024）
国家重点专项研发计划(2018YFB2100500) （2018YFB2100500）
