TY - GEN T1 - Remote Sensing Image Classification and Semantic Segmentation A2 - Li, Jiaojiao LA - eng PB - MDPI - Multidisciplinary Digital Publishing Institute YR - 2024 UL - https://ebooks.jgu.edu.in/Record/doab-20.500.12854-143754 AB - With the rapid growth in remote sensing imaging technology, vast amounts of remote sensing data are generated, which is significant for land-monitoring systems, and agriculture, etc., for Earth, Mars, etc. In recent decades, deep learning techniques have had a significant effect on remote sensing data processing, especially in image classification and semantic segmentation. However, several challenges still exist due to the limited annotations, the complexity of large-scale areas, and other specific problems, which make it more difficult in real-world applications. Therefore, novel deep neural networks combined with meta-learning, attention mechanisms, or other new transformer technologies need to be given more attention in remote sensing. It is also necessary to develop lightweight, explainable, and robust networks. Moreover, this Special Issue aims to develop state-of-the-art deep networks for more accurate remote sensing image classification and semantic segmentation, which also aims to achieve an efficient cross-domain performance through a lightweight network design. SN - 9783725813650 SN - 9783725813667 KW - Mars terrain segmentation KW - semantic segmentation KW - planetary exploration KW - transformer KW - channel attention module KW - hybrid structure KW - 3D convolutional neural network KW - noisy hyperspectral image KW - Tucker tensor decomposition KW - spectral–spatial feature extraction KW - high-resolution remote sensing KW - self-attention KW - context modeling KW - feature alignment KW - remote sensing KW - adapter KW - active–passive remote sensing KW - canopy height model (CHM) KW - classification KW - random forest (RF) KW - spectral reconstruction KW - convolutional transformer KW - hyperspectral unmixing KW - multi-head self-attention KW - hyperspectral image KW - context information KW - convolutional neural network KW - attention module KW - model compression KW - neural network pruning KW - frequency domain KW - lightweight deep neural networks KW - remote sensing image classification KW - deep space exploration KW - planetary rover KW - rock segmentation KW - double-branch KW - sea–land segmentation KW - GF-6 KW - CNN KW - global context information KW - fine-grained feature KW - feature fusion KW - polarimetric synthetic aperture radar (PolSAR) image classification KW - complex-valued convolutional neural network KW - complex-valued max pooling KW - complex-valued nonlinear activation KW - complex-valued cross-entropy KW - meta-learning KW - cross-domain segmentation KW - few-shot semantic segmentation KW - satellite imagery KW - scene segmentation KW - deep generative models KW - mine waste rock KW - leaching waste dumps KW - physical stability KW - closure planning KW - semantic segmentation in foggy scenes KW - unsupervised domain adaptation KW - UDA KW - self-training KW - label correction KW - self-distillation contrastive learning KW - sample rebalancing KW - hyperspectral KW - LiDAR KW - fusion classification KW - remote sensing scene classification KW - few-shot learning KW - data augmentation KW - feature distortion KW - segment anything model (SAM) KW - semantic road scene segmentation KW - image semantic segmentation KW - instruction set architecture (ISA) KW - field programmable gate array (FPGA) KW - spacecraft component images KW - land cover classification KW - SAR and optical images KW - attention mechanism KW - multi-scale feature fusion KW - high-resolution remote sensing images KW - ASPP module KW - local attention network model KW - activation function KW - point cloud semantic segmentation KW - multi-spatial feature encoding KW - multi-head attention pooling KW - cloud shadow segmentation KW - convolution neural network KW - deep learning KW - polarimetric synthetic aperture radar (PolSAR) KW - reflection symmetric decomposition (RSD) KW - data input scheme KW - land classification KW - polarimetric scattering characteristics KW - thema EDItEUR::U Computing and Information Technology KW - thema EDItEUR::U Computing and Information Technology::UY Computer science ER -