Deep Diffusion Processes for Active Learning of Hyperspectral Images

2021/01/08 by Tasissa, Abiy, Nguyen, Duc, Murphy, James
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2101.03197

Abstract

A method for active learning of hyperspectral images (HSI) is proposed, which combines deep learning with diffusion processes on graphs. A deep variational autoencoder extracts smoothed, denoised features from a high-dimensional HSI, which are then used to make labeling queries based on graph diffusion processes. The proposed method combines the robust representations of deep learning with the mathematical tractability of diffusion geometry, and leads to strong performance on real HSI.

Related

• Learning by Active Nonlinear Diffusion
• Spatially regularized active diffusion learning for high-dimensional images
• Active Deep Learning for Classification of Hyperspectral Images
• Unsupervised Clustering and Active Learning of Hyperspectral Images with Nonlinear Diffusion
• DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification