计算机工程与应用2024，Vol.60Issue(19)：110-119,10.DOI:10.3778/j.issn.1002-8331.2308-0446
基于知识蒸馏的道路交通标志识别神经网络
Lightweight Road Traffic Sign Identification Neural Network Based on Knowledge Distillation
摘要
Abstract
Recognition of traffic signs in natural scenes is susceptible to interference from factors such as lighting,occlu-sions,and blurriness,which can affect detection accuracy.Additionally,existing deep learning models have a large num-ber of parameters and high computational complexity,resulting in longer model inference times.The article proposes a neural network architecture adaptive feature extraction-vision Transformer(AFE-ViT)based on knowledge distillation for road traffic sign recognition.The architecture consists of an adaptive feature extraction module and a lightweight vision Transformer(ViT)classifier.It combines local and global feature information in the image,and has better adaptability to road traffic sign recognition in natural scenes.Among them,the adaptive feature extraction module combines Inception-NetV1,SKNet ideas and residual structure to realize the adaptive selection of multiple receptive fields,and as the front module of ViT,it effectively improves the efficiency of feature extraction.It chooses ResNet18 as the teacher network and AFE-ViT as the student network,and uses feature-level and output-level knowledge distillation methods to distill AFE-ViT and compress model parameters.The experimental results show that the recognition accuracy of this method can reach 98.98%,and the number of model parameters is only 9.9×105,which is better than similar deep learning models.关键词
交通标识/知识蒸馏/自适应特征提取Key words
traffic sign identification/knowledge distillation/adaptive feature extraction分类
信息技术与安全科学引用本文复制引用
葛怡源,于明鑫..基于知识蒸馏的道路交通标志识别神经网络[J].计算机工程与应用,2024,60(19):110-119,10.基金项目
国家自然科学基金(U21A6003) （U21A6003）
北京信息科技大学勤信英才项目(5112111145). （5112111145）
