• Corpus ID: 239050243

3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification

  title={3D-ANAS v2: Grafting Transformer Module on Automatically Designed ConvNet for Hyperspectral Image Classification},
  author={Xizhe Xue and Haokui Zhang and Zongwen Bai and Ying Li},
  • Xizhe Xue, Haokui Zhang, +1 author Ying Li
  • Published 21 October 2021
  • Computer Science
  • ArXiv
Hyperspectral image (HSI) classification has been a hot topic for decides, as Hyperspectral image has rich spatial and spectral information, providing strong basis for distinguishing different land-cover objects. Benefiting from the development of deep learning technologies, deep learning based HSI classification methods have achieved promising performance. Recently, several neural architecture search (NAS) algorithms are proposed for HSI classification, which further improve the accuracy of… 


3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification
A 3D asymmetric neural network search algorithm is proposed and used to automatically search for efficient architectures for HSI classifications, and a new fast classification framework is proposed, i.e., pixel-to-pixel classification framework, which has no repetitive operations and reduces the overall cost.
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.
Spectral-spatial classification of hyperspectral imagery using a dual-channel convolutional neural network
A novel dual-channel convolutional neural network framework is proposed for accurate spectral-spatial classification of hyperspectral image (HSI) and demonstrates that the DC-CNN-based method outperforms the state-of-the-art methods by a considerable margin.
Automatic Design of Convolutional Neural Network for Hyperspectral Image Classification
The experiments show that the automatically designed data-dependent CNNs obtain competitive classification accuracy compared with the state-of-the-art methods and open a new window for future research, showing the huge potential of using neural architectures’ optimization capabilities for the accurate HSI classification.
Spectral-spatial classification of hyperspectral imagery based on deep convolutional network
  • Haokui Zhang, Y. Li
  • Computer Science
    2016 International Conference on Orange Technologies (ICOT)
  • 2016
Inspired by the excellent performance of deep convolutional neural network (DCNN) in visual image classification, DCNN is introduced into HSI classification and one-dimension kernels are adopted in the authors' DCNN to fit the HSI context.
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.
Spectral-spatial classification of hyperspectral image using autoencoders
A new framework of spectral-spatial feature extraction for HSI classification, in which for the first time the concept of deep learning is introduced, and achieves the highest classification accuracy among all methods, and outperforms classical classifiers such as SVM and PCA-based SVM.
Spectral–Spatial Classification of Hyperspectral Image Based on Deep Auto-Encoder
Using collaborative representation-based classification with deep features makes the proposed classifier extremely robust under a small training set, and the proposed method provides encouraging results compared with some related techniques.
Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
An end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as3-D-LWNet) for limited samples-based HSI classification has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance.
Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network
  • Yushi Chen, Xing Zhao, X. Jia
  • Computer 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.