DeepAI AI Chat
Log In Sign Up

Cross-domain CNN for Hyperspectral Image Classification

by   Hyungtae Lee, et al.
Booz Allen Hamilton Inc.
Department of Defense

In this paper, we address the dataset scarcity issue with the hyperspectral image classification. As only a few thousands of pixels are available for training, it is difficult to effectively learn high-capacity Convolutional Neural Networks (CNNs). To cope with this problem, we propose a novel cross-domain CNN containing the shared parameters which can co-learn across multiple hyperspectral datasets. The network also contains the non-shared portions designed to handle the dataset specific spectral characteristics and the associated classification tasks. Our approach is the first attempt to learn a CNN for multiple hyperspectral datasets, in an end-to-end fashion. Moreover, we have experimentally shown that the proposed network trained on three of the widely used datasets outperform all the baseline networks which are trained on single dataset.


Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification

A pretrain-finetune strategy is widely used to reduce the overfitting th...

Domain Adaptor Networks for Hyperspectral Image Recognition

We consider the problem of adapting a network trained on three-channel c...

Boosting Deep Hyperspectral Image Classification with Spectral Unmixing

Recent advances in neural networks have made great progress in addressin...

Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data

Soil texture is important for many environmental processes. In this pape...

Is Pretraining Necessary for Hyperspectral Image Classification?

We address two questions for training a convolutional neural network (CN...

A CNN With Multi-scale Convolution for Hyperspectral Image Classification using Target-Pixel-Orientation scheme

Recently, CNN is a popular choice to handle the hyperspectral image clas...