高技术通讯2026，Vol.36Issue(7)：688-700,13.DOI:10.3772/j.issn.1002-0470.2026.07.003
基于特征拟合蒸馏度量网络的低分辨率人脸识别
Feature fitting distillation metric network for low-resolution face recognition
摘要
Abstract
Face recognition systems often capture low-resolution facial images in practical applications where a significant amount of facial detail features are lost.Additionally,the presence of superimposed interference factors,such as il-lumination variations,occlusions,and pose changes,makes it challenging for existing classical face recognition al-gorithms to achieve satisfactory recognition accuracy that meets real-world application requirements.To address these issues,we propose a feature fitting distillation metric(FFDM)network.First,feature fitting distillation is performed between multiple stages of convolutional layers in both the teacher network and student network,enabling the features extracted by each convolutional layer in the student network to approximate those of the corresponding layers in the teacher network as closely as possible.This approach aims to enhance the student network's capability in characterizing features from low-resolution samples.Subsequently,a similarity metric distillation loss function is introduced between the similarity measurement sub-networks of the teacher and student networks.The student net-work learns the powerful classification capability of the teacher network for fine-grained features through this distil-lation loss function,thus enabling the student network to have high robustness in complex and unconstrained sce-narios.Finally,the experimental results on multiple datasets demonstrate that FFDM model exhibits higher accura-cy and superior generalization capability in low-resolution face recognition tasks.关键词
特征拟合蒸馏/相似度量蒸馏/低分辨率人脸识别/非限制性场景Key words
feature fitting distillation/similarity metric distillation/low-resolution face recognition/non-re-strictive scenarios引用本文复制引用
钟锐,刘林彬,陈斌..基于特征拟合蒸馏度量网络的低分辨率人脸识别[J].高技术通讯,2026,36(7):688-700,13.基金项目
国家自然科学基金(62266003),江西省自然科学基金(20232BAB202056),江西省教育厅科技项目(GJJ211401),江西省基础教育研究课题(SZUGSXX2024-1068)和赣南师范大学研究生创新基金项目(YCXJ24-B12)资助. （62266003）
