• Corpus ID: 85499343

1D-Convolutional Capsule Network for Hyperspectral Image Classification

@article{Zhang20191DConvolutionalCN,
  title={1D-Convolutional Capsule Network for Hyperspectral Image Classification},
  author={Haitao Zhang and Lingguo Meng and Xian Wei and Xiaoliang Tang and Xuan Tang and Xingping Wang and Bo Jin and Wei Yao},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.09834}
}
Recently, convolutional neural networks (CNNs) have achieved excellent performances in many computer vision tasks. Specifically, for hyperspectral images (HSIs) classification, CNNs often require very complex structure due to the high dimension of HSIs. The complex structure of CNNs results in prohibitive training efforts. Moreover, the common situation in HSIs classification task is the lack of labeled samples, which results in accuracy deterioration of CNNs. In this work, we develop an easy… 

Spectral–Spatial Hyperspectral Image Classification Using Dual-Channel Capsule Networks

This letter proposes a new network architecture based on the CapsNet for HSI classification tasks, called dual-channel capsule network (DCCapsNet), which was trained and validated on four real HSI data sets and achieved high accuracy.

Multiscale Feature Aggregation Capsule Neural Network for Hyperspectral Remote Sensing Image Classification

This study proposes a multiscale feature aggregation capsule neural network (MS-CapsNet) based on CapsNet via the implementation of two branches that simultaneously extract spectral, local spatial, and global spatial features to integrate multiscales features and improve model robustness.

A Lightweight Convolutional Neural Network for Hyperspectral Image Classification

Experimental results illustrate that the developed LWCNN approach is advantageous in both the efficiency and robustness sides for hyperspectral image classification tasks and outperforms other state-of-the-art methods (both traditional-based and DL-based) with very limited labeled samples.

A non-local capsule neural network for hyperspectral remote sensing image classification

The proposed NLCapsNet can effectively enhance the classification accuracy with a rapid convergence speed and avoid overfitting when the number of training samples is limited.

Multi-stack hybrid CNN with non-monotonic activation functions for hyperspectral satellite image classification

This paper proposes a variant of the 3D-2D CNN Hybrid model to extract representational features from a different class of land use land cover using different receptive fields in a multi-stack arrangement and explores through experimentation the possible replacement of monotonic activation function ReLu using non-monotonic functions.

Capsule Networks - A survey

Deep Learning-Based Phenological Event Modeling for Classification of Crops

The proposed architecture, called the variational capsule network (VCapsNet), significantly improves the classification and denoising results and is less sensitive to noise and yields good results, even at shallower depths, compared to the main existing approaches.

Deep Learning-Based Phenological Event Modeling for Classification of Crops

It was observed that the regularization of classification using the reconstruction loss and that of denoising using the label information priors improve the generalizability and convergence of the network, and this study illustrates the use of interpretability-based evaluation measures.

Surface Defect Detection of Wet-Blue Leather Using Hyperspectral Imaging

This paper is the first to use hyperspectral imaging (HSI) to implement the surface inspection of five wet-blue leather defects including brand masks, rotten grain, rupture, insect bites, and scratches in the pixel level detection and demonstrated that the overall performance of WBS was better than the original CEM.

References

SHOWING 1-10 OF 42 REFERENCES

Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network

A 3D convolutional neural network framework is proposed for accurate HSI classification, which is lighter, less likely to over-fit, and easier to train, and requires fewer parameters than other deep learning-based methods.

Multi-scale 3D deep convolutional neural network for hyperspectral image classification

  • Mingyi HeBo LiHuahui Chen
  • Computer Science, Environmental Science
    2017 IEEE International Conference on Image Processing (ICIP)
  • 2017
A Multiscale 3D deep convolutional neural network (M3D-DCNN) is proposed for HSI classification, which could jointly learn both 2D Multi-scale spatial feature and 1D spectral feature from HSI data in an end-to-end approach, promising to achieve better results with large-scale dataset.

Hyperspectral Image Classification Based on Deep Deconvolution Network With Skip Architecture

An end-to-end deconvolution network with skip architecture to learn the spectral–spatial features and experimental results reveal the competitive performance of the proposed approach over several related methods.

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

This paper proposes a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery and reveals that the proposed models with sparse constraints provide competitive results to state-of-the-art methods.

A semi-supervised convolutional neural network for hyperspectral image classification

A novel semi-supervised convolutional neural network is proposed for the classification of hyperspectral image that can automatically learn features from complex hyperspectRAL image data structures and simultaneously minimize the sum of supervised and unsupervised cost functions.

Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification

Experiments demonstrate that the learned deep joint spectral–spatial features are discriminative, and competitive classification results can be achieved when compared with state-of-the-art methods.

Deep Learning-Based Classification of Hyperspectral Data

The concept of deep learning is introduced into hyperspectral data classification for the first time, and a new way of classifying with spatial-dominated information is proposed, which is a hybrid of principle component analysis (PCA), deep learning architecture, and logistic regression.

Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network

  • Yushi ChenXing ZhaoX. Jia
  • Computer Science, Environmental Science
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2015
A new feature extraction (FE) and image classification framework are proposed for hyperspectral data analysis based on deep belief network (DBN) and a novel deep architecture is proposed, which combines the spectral-spatial FE and classification together to get high classification accuracy.

Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network

A new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework and achieves better performance on one synthetic data set and two benchmark HSI data sets in a number of experimental settings.

Capsules for Object Segmentation

The proposed convolutional-deconvolutional capsule network, called SegCaps, shows strong results for the task of object segmentation with substantial decrease in parameter space and is able to handle large image sizes as opposed to baseline capsules.