Learning to Diversify Deep Belief Networks for Hyperspectral Image Classification

By Ping Zhong, Zhiqiang Gong, Shutao Li, Carola-Bibiane Schönlieb. IEEE Transactions on Geoscience and Remote Sensing, 2017

321 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/0e7e22fe094b0e4b0aa67d4915072c598512da35

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images (2018, methodology): “The model has been applied with success in a variety of natural scene images and remote sensing images [21], [48], [49].”
Hyperspectral Image Classification With Deep Feature Fusion Network (2018, background): “In addition, a deep belief network (DBN), as another deep model, is also proposed for HSI classification [41], [42].”
Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification (2019, background): “To address this defect, deep learning [15], [16], [17], [18] has been extensively employed for hyperspectral image classiﬁ-cation and has attracted increasing attention for its strong representation ability.”
Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, methodology): “To mitigate these two problems, [191] introduced a diversified DBN model through regularizing the pretraining and fine-tuning process by imposing a diversity prior to enhancing the DBN’s classification accuracy for HSI.”
Spatial-Spectral Transformer for Hyperspectral Image Classification (2021, methodology): “After that, several deep learning models such as the deep belief network [20], CNN [21,22], recurrent neural network [23,24], generative adversarial network [25,26], and capsule network [27,28] were investigated for HSI classification and obtained good classification performance.”
Going Deeper With Contextual CNN for Hyperspectral Image Classification (2016, methodology): “The limited access to large scale hyperspectral data has been preventing existing CNNbased approaches for HSI classification [1]–[6] from leveraging deeper and wider networks that can potentially better exploit very rich spectral and spatial information contained in hypersepctral images.”
Deep Learning for Hyperspectral Image Classification: An Overview (2019, methodology): “For example, research works [35], [37], [53], [54], [73], [104], [111], [116] utilized a fully connected network to classify HSIs, where the training of the network was divided into pretraining in an unsupervised manner and fine-tuning with labeled data.”
Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification (2019, background): “[39] introduced a diversity promoting prior into the pretraining (unsupervised) and fine-tuning proce-”
Generative Adversarial Networks for Hyperspectral Image Classification (2018, methodology): “Deep belief network, another kind of deep models, was introduced and modified for HSI classification as well [17], [18].”
Cascaded Recurrent Neural Networks for Hyperspectral Image Classification (2017, background): “Similar to autoencoder, deep belief network was also explored to extract spectral features [29]–[31].”