Multi-sensor image can provide supplementary information, usually leading to better performance in classification tasks. However, the general deep neural network-based multi-sensor classification method learns each sensor image separately, followed by a stacked concentrate for feature fusion. This way requires a large time cost for network training, and insufficient feature fusion may cause. Considering efficient multi-sensor feature extraction and fusion with a lightweight network, this paper proposes an attention-guided classification method (AGCNet), especially for multispectral (MS) and panchromatic (PAN) image classification. In the proposed method, a share-split network (SSNet) including a shared branch and multiple split branches performs feature extraction for each sensor image, where the shared branch learns basis features of MS and PAN images with fewer learn-able parameters, and the split branch extracts the privileged features of each sensor image via multiple task-specific attention units. Furthermore, a selective classification network (SCNet) with a selective kernel unit is used for adaptive feature fusion. The proposed AGCNet can be trained by an end-to-end fashion without manual intervention. The experimental results are reported on four MS and PAN datasets, and compared with state-of-the-art methods. The classification maps and accuracies show the superiority of the proposed AGCNet model.
The number of labeled samples has a great impact on the classification results of very high-resolution (VHR) remote sensing image. However, the acquisition of available labeled samples is difficult and time-consuming. Faced with the limited labeled samples on high-resolution remote sensing image, semisupervised method becomes an effective way. In semi-supervised learning, accurate similarity prediction between unlabeled and labeled samples is very important. However, reliable similarity prediction between high-dimensional features is difficult. For more reliable similarity prediction for high-dimensional feature, a novel semi-supervised classification framework via improved metric learning (IML) with convolutional neural network (CNN) is proposed. In the proposed method, a novel trainable metric learning network is designed to accurately evaluate the similarity between high-dimension features. The vector distance parameter solving problem is transformed into a neural network design problem, which can automatically calculate parameters by BP algorithm. Finally, the pixel constraint mechanism is introduced to select the unlabeled samples. Experimental results conducted on three VHR remote sensing images, including Aerial, Xi'an, and Pavia University, and the results present that the proposed method performs better than the compared state-of-the-art methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.