• Corpus ID: 232269985

TPPI-Net: Towards Efficient and Practical Hyperspectral Image Classification

@article{Chen2021TPPINetTE,
  title={TPPI-Net: Towards Efficient and Practical Hyperspectral Image Classification},
  author={Hao Chen and Xiaohua Li and Jiliu Zhou},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.10084}
}
Hyperspectral Image(HSI) classification is the most vibrant field of research in the hyperspectral community, which aims to assign each pixel in the image to one certain category based on its spectral-spatial characteristics. Recently, some spectral-spatial-feature based DCNNs have been proposed and demonstrated remarkable classification performance. When facing a real HSI, however, these Networks have to deal with the pixels in the image one by one. The pixel-wise processing strategy is… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 40 REFERENCES

Hyperspectral Image Classification Using Deep Pixel-Pair Features

TLDR
Experimental results based on several hyperspectral image data sets demonstrate that the proposed pixel-pair method can achieve better classification performance than the conventional deep learning-based method.

Obesity May Be Bad: Compressed Convolutional Networks for Biomedical Image Segmentation

TLDR
The Optimum Mimic Backbone (OMB) is introduced, which can force compressed CNN mimics what the original CNN behaves in optimal situations and gets higher IoU scores than other state-of-the-art compression techniques in experiments on four popular, different biomedical image segmentation datasets.

Deep Learning for Hyperspectral Image Classification: An Overview

TLDR
This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies to improve classification performance, which can provide some guidelines for future studies on this topic.

Hyperspectral Classification Based on Siamese Neural Network Using Spectral-Spatial Feature

  • Shizhi ZhaoWei LiQ. DuQiong Ran
  • Computer Science, Environmental Science
    IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
  • 2018
TLDR
A novel pixel-pair method based on Siamese neural network (SNN) is employed to significantly enlarge the training set and better represent the spectral-spatial features in hyperspectral image classification.

Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification

TLDR
A new deep CNN architecture specially designed for the HSI data is presented to improve the spectral–spatial features uncovered by the convolutional filters of the network and is able to provide competitive advantages over the state-of-the-art HSI classification methods.

Hyperspectral Image Classification With Deep Learning Models

TLDR
This paper advocates four new deep learning models, namely, 2-D convolutional neural network, 3-D-CNN, recurrent 2- D CNN, recurrent R-2-D CNN, and recurrent 3- D-CNN for hyperspectral image classification.

3-D Deep Learning Approach for Remote Sensing Image Classification

TLDR
The aim of this paper is first to explore the performance of DL architectures for the RS hyperspectral data set classification and second to introduce a new 3-D DL approach that enables a joint spectral and spatial information process.

Hyperspectral Image Classification With Deep Feature Fusion Network

TLDR
A deep feature fusion network (DFFN) is proposed for HSI classification that fuses the outputs of different hierarchical layers, which can further improve the classification accuracy and outperforms other competitive classifiers.

Mask R-CNN

TLDR
This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners.

Diverse Region-Based CNN for Hyperspectral Image Classification

TLDR
Experimental results with widely used hyperspectral image data sets demonstrate that the proposed classification framework, called diverse region-based CNN, can surpass any other conventional deep learning-based classifiers and other state-of-the-art classifiers.