期刊
REMOTE SENSING
卷 15, 期 20, 页码 -出版社
MDPI
DOI: 10.3390/rs15204979
关键词
multi-label; attention; remote sensing; land cover
This study proposes a multi-label classification model for multi-source remote sensing images that combines dense convolution and an attention mechanism. The model enhances feature extraction and classification accuracy by adding fusion channel attention and a spatial attention mechanism, as well as replacing the softmax activation function with the sigmoid activation function.
For the multi-label classification task of remote sensing images (RSIs), it is difficult to accurately extract feature information from complex land covers, and it is easy to generate redundant features by ordinary convolution extraction features. This paper proposes a multi-label classification model for multi-source RSIs that combines dense convolution and an attention mechanism. This method adds fusion channel attention and a spatial attention mechanism to each dense block module of the DenseNet, and the sigmoid activation function replaces the softmax activation function in multi-label classification. The improved model retains the main features of RSIs to the greatest extent and enhances the feature extraction of the images. The model can integrate local features, capture global dependencies, and aggregate contextual information to improve the multi-label land cover classification accuracy of RSIs. We conducted comparative experiments on the SEN12-MS and UC-Merced land cover dataset and analyzed the evaluation indicators. The experimental results show that this method effectively improves the multi-label classification accuracy of RSIs.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据