封皓元,段 勇.基于深度迁移学习的天气图像识别[J].电子测量与仪器学报,2023,37(4):223-230 |
基于深度迁移学习的天气图像识别 |
Weather image recognition based on fusing deep transfer learning |
|
DOI: |
中文关键词: 模型融合 深度学习 迁移学习 领域自适应 天气识别 |
英文关键词:model fusion deep learning transfer learning domain adaptation weather recognition |
基金项目:辽宁省高等学校优秀科技人才支持计划(LR15045)项目资助 |
|
|
摘要点击次数: 1182 |
全文下载次数: 1676 |
中文摘要: |
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。 |
英文摘要: |
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. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|