基于迁移学习和通道注意力的遥感图像场景分类
Remote sensing image scene classification based on transfer learn-ing and channel attention
舒薪行 1温显斌 2袁立明 2徐海霞 2史芙蓉2
作者信息
- 1. 天津理工大学计算机科学与工程学院,天津 300384;计算机视觉与系统教育部重点实验室,天津 300384;中国民航科学技术研究院研发中心,北京 100028
- 2. 天津理工大学计算机科学与工程学院,天津 300384;计算机视觉与系统教育部重点实验室,天津 300384
- 折叠
摘要
针对遥感图像场景分类任务中训练样本数量少及遥感图像背景复杂等问题,本文将迁移学习和通道注意力引入到卷积神经网络(convolutional neural network,CNN)中,提出基于迁移学习和通道注意力的遥感图像场景分类方法.该方法首先选用经过ImageNet自然数据集预训练的两个CNN作为主干,同时引入通道注意力机制,自适应地增强主要特征,抑制次要特征;然后融合这两个网络提取的特征进行分类;最后采用微调迁移学习的方式实现目标域上的学习与分类.提出的方法在几个经典的公共数据集上进行了评估,实验结果证明了本文提出的方法在遥感图像场景分类中达到与其他先进方法相当的性能.
Abstract
In order to solve the problems of small number of training samples and complex background of remote sensing images,this paper introduces transfer learning and channel attention into convolutional neural network(CNN),and proposes a remote sensing image scene classification method based on trans-fer learning and channel attention.Firstly,this method selects two CNNs pre-trained by ImageNet natu-ral dataset as the backbone,and introduces the channel attention mechanism to adaptively enhance the main features and suppress the secondary features.Then the features extracted from these two networks are fused for classification.Finally,fine-tuning transfer learning is used to realize learning and classifica-tion in the target domain.The proposed method is evaluated on several classical public datasets,and the experimental results show that the proposed method achieves the same performance as other advanced methods in remote sensing image scene classification.
关键词
遥感图像/场景分类/卷积神经网络(CNN)/迁移学习/通道注意力Key words
remote sensing image/scene classification/convolutional neural network(CNN)/transfer learning/channel attention引用本文复制引用
基金项目
天津市新一代人工智能科技重大专项基金(18ZXZNGX00150)
天津市技术创新引导专项(21YDTPJC00250)
出版年
2024
NETL
NSTL
万方数据