摘要
当对天气图像等场景复杂和特征不明显的图像进行识别时,往往存在识别率不高和特征冗余等问题。基于此,本文提出了一种基于深度迁移学习的图像分类算法。该算法利用ImageNet数据集的模型参数构建ResNeXt、Xception以及SENet 3种网络模型提取图像特征,采用领域自适应的判别联合分布自适应算法来相似化特征向量,完成高质量的特征表示,并以其结果为准则融合模型特征,将融合特征经过多层感知机训练以实现高准确率识别的图像分类。实验结果表明,该算法的性能优于传统的单一网络模型,进一步提升了图像分类准确率的上限。
When recognizing images with complex scenes and obscure features such as weather images,there are often problems such as low recognition rate and feature redundancy.Based on this,an image classification algorithm based on deep transfer learning is proposed in this paper.The algorithm uses the model parameters of ImageNet dataset to construct three network models,ResNeXt,Xception and SENet,to extract image features,and uses a domain-adaptive discriminative joint distribution adaptive algorithm to resemble the feature vectors to complete a high-quality feature representation,and uses the result as a criterion to fuse the model features,and trains the fused features through a multilayer perceptron to achieve image classification with high accuracy recognition.The experimental results show that the algorithm outperforms the traditional single network model and further improves the upper limit of image classification accuracy.
作者
封皓元
段勇
Feng Haoyuan;Duan Yong(School of Information Science and Engineering,Shenyang University of Technology,Shenyang 110870,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2023年第4期223-230,共8页
Journal of Electronic Measurement and Instrumentation
基金
辽宁省高等学校优秀科技人才支持计划(LR15045)项目资助。
关键词
模型融合
深度学习
迁移学习
领域自适应
天气识别
model fusion
deep learning
transfer learning
domain adaptation
weather recognition
作者简介
封皓元,2020年于中国石油大学胜利学院获得学士学位,现为沈阳工业大学硕士研究生,主要研究方向为计算机视觉、深度学习。E-mail:fhy_private@163.com;通信作者:段勇,沈阳工业大学信息科学与工程学院教授,博士生导师,主要研究方向为自主机器人、机器学习、计算机视觉。E-mail:duanyong0607@126.com。
