Learning multiscale and deep representations for classifying remotely sensed imagery

By Wenzhi Zhao, Shihong Du. 2016

375 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/49595205981e115d85f1445429694909a1a25040

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach (2016, result): “However, the configuration of CNN can greatly affect the classification accuracies in terms of spatial feature extraction as we reported in previous works [29]–[31].”
UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery (2021, neutral): “Since then, CNN-based methods have dominated the semantic segmentation task in the remote sensing field (Kemker et al., 2018; Kotaridis and Lazaridou, 2021; Ma et al., 2019; Tong et al., 2020; Zhao and Du, 2016; Zhu et al., 2017).”
Land-cover classification with high-resolution remote sensing images using transferable deep models (2018, methodology): “Recently, deep neural network models have been intensively studied to address the task of land-cover classiﬁcation and reported impressive performance, see e.g. [34–36 , 63–65].”
Scene classification using multi-scale deeply described visual words (2016, methodology): “In these studies, CNNs were considered as the black box of image classi ﬁ er (Hu, Xia, Wang, et al. 2015; Zhao et al. 2015; Hu, Xia, Hu, et al. 2015; Zhao and Du 2016a), which do not have access to the analysis of characteristics of scenes.”
A review of deep learning methods for semantic segmentation of remote sensing imagery (2021, background): “Each FCN is trained with a different initialization from ImageNet (Russa-kovsky et al., 2015), Pascal VOC (Everingham, Van Gool, Williams, Winn, & Zisserman, 2010), and Places (Zhou, Lapedriza, Xiao, Torralba, & Oliva, 2014) data sets.”
Building Instance Classification Using Street View Images (2018, methodology): “To improve the composition-based inference of land-use classes, multiscale CNN-based approaches are developed in [43, 44, 45].”
Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, background): “One common solution is multi-scale learning: the authors of [151] propose a multi-scale CNN framework in which a pyramid of differently scaled versions of the high-resolution image sample is fed to the machine to capture the different conceptual information.”
3-D Deep Learning Approach for Remote Sensing Image Classification (2018, background): “The same problem was seen when only processing the spatial content of the data as detailed in [34], [35], [36] and [37].”
A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification (2017, methodology): “…imagery, a deep CNN model was formulated through a greedy layer-wise 90 unsupervised pre-training strategy (Romero et al., 2016), whereas an image pyramid 91 was built up through upscaling the original image to capture the contextual information 92 at multiple scales (Zhao and Du, 2016).”
Deep Learning Advances in Computer Vision with 3D Data (2017, methodology): “A Multiscale CNN was used in the approach of Zhao and Du [2016].”
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, methodology): “To address this problem, a number of DL-based featurelearning methods have been proposed to find a new way of extracting the deep spectral–spatial representation for classification [84].”
Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification (2017, methodology): “Furthermore, the spectral features in [26] and [31] were obtained by shallow dimensionality reduction features that are more abstract and”
Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks (2016, methodology): “Multi-scale processing has been proven effective for classification, notably in the Inception network [30], for semantic segmentation [8] and on remote sensing imagery [21].”
Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification (2017, neutral): “at multiple spatial scales has also been exploited, notably for hyperspectral classification [22], [23] and image segmenta-”
Deep learning in environmental remote sensing: Achievements and challenges (2020, methodology): “Accordingly, DL has been successfully applied to land cover classification and achieved impressive results (Zhang et al., 2018a; Zhao and Du, 2016; Zhao et al., 2015).”