Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework

By Zilong Zhong, Jonathan Li, Zhiming Luo, Michael A. Chapman. IEEE Transactions on Geoscience and Remote Sensing, 2018

1,589 citations recorded by the source corpus.

Subfields: Atmospheric Science, Biomedical Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/18056fcac6fc744b940a8d10ff36d42269006f3c

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 Biomedical Engineering

In Media Technology

Citations in the corpus

Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox (2020, methodology): “In [115], a serial structure was also used to extract spectral-spatial features.”
HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers (2020, background): “Recently, deep learning-based deep spatial–spectral feature extractors [2], [8], [20]–[23] have been widely used by the remote sensing community, and some of them have achieved”
Spectral–Spatial Feature Tokenization Transformer for Hyperspectral Image Classification (2022, methodology): “With the prevalence of residual networks in the ﬁeld of image classiﬁcation, Zhong et al. [42] proposed a spatial–spectral residual network to classify HSI.”
Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification (2019, methodology): “Even though the spectral–spatial classifiers 3-D-CNN, SSRN, and DFCNN have shown to obtain relatively high classification accuracies, the proposed architecture provides a more effective scheme to reduce the uncertainty when uncovering spectral–spatial features.”
CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification (2020, methodology): “Besides, the residual and dense connections have also been introduced to HSI classiﬁcation [33], [34].”
A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification (2021, methodology): “9 (a)-(g) illustrates the classification results using RBF-SVM, SS-CNN, SSRN, DBMA, MCNN-CONVLSTM, U-Net and FPGA.”
Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, methodology): “To extract discriminative joint representation [188] introduced a Supervised Spectral-Spatial Residual Network (SSRN) that uses a series of 3D convolutions in the respective spectral and spatial residual blocks.”
A Fast Dense Spectral-Spatial Convolution Network Framework for Hyperspectral Images Classification (2018, methodology): “In our experiment, we compared the proposed FDSSC framework to other deep-learning-based methods, that is, SAE-LR [8], CNN [9], 3D-CNN-LR [11], and the state-of-art SSRN method [13] (only for labeled pixels).”
Deep Learning for Hyperspectral Image Classification: An Overview (2019, methodology): “In addition, research works [87], [88], [93], [97], [98] introduce RL [100] to build a very deep network with the purpose of extracting more discriminative features for HSI classification.”
Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network (2019, methodology): “Unlike traditional pixel-based methods that only use spectral features, 3D-cube-based methods like SSRN [31], FDSSC [32], DBMA [34], and our proposed framework exploit both spectral and spatial information.”
Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review (2019, methodology): “D approach was proposed in [159] and recently in [160].”
Unsupervised Single-Scene Semantic Segmentation for Earth Observation (2022, background): “ence of only the target scene and no additional scene [14], [15].”
A survey: Deep learning for hyperspectral image classification with few labeled samples (2021, result): “Similar to the trend of autoencoder-based classification methods, three-dimensional CNN models have also been applied to HSI classification in recent years and have shown better feature fusion capabilities [54, 55].”
Attention-Based Adaptive Spectral–Spatial Kernel ResNet for Hyperspectral Image Classification (2020, methodology): “[32] introduced a supervised spectral–spatial”
Multimodal Fusion Transformer for Remote Sensing Image Classification (2022, background): “Zhong et al. designed a spectral-spatial residual network (SSRN) that can better utilize both spectral and spatial information for enhanced classiﬁcation [37].”
Hyperspectral Imaging: A Review on UAV-Based Sensors, Data Processing and Applications for Agriculture and Forestry (2017, background): “The spectral-spatial residual network found in [120] consists of a supervised deep learning framework that is capable of discriminating features from abundant spectral signatures and spatial contexts in a HSI (provided as input and without the need for feature engineering).”
Spectral–Spatial Morphological Attention Transformer for Hyperspectral Image Classification (2023, methodology): “Zhong et al. [33] introduced a spatial–spectral ResNet (SSRN) for utilizing both spatial and spectral information to obtain enhanced classification performance.”
Capsule Networks for Hyperspectral Image Classification (2019, background): “As shown in the results reported on Table VI, the proposed network architecture consistently outperforms the SSRN for most tested conﬁgurations.”
Spatial-Spectral Transformer for Hyperspectral Image Classification (2021, methodology): “In [34], the 3-D convolutional layer and batch normalization layer were utilized to extract spectral–spatial information and regularize the model, respectively.”