BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

Abstract

Deep learning based landcover classification algorithms have recently been proposed in literature. In hyperspectral images (HSI) they face the challenges of large dimensionality, spatial variability of spectral signatures and scarcity of labeled data. In this article we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs landcover classification. The architecture has fewer independent connection weights and thus requires lesser number of training data. The method is found to outperform the highest reported accuracies on popular hyperspectral image data sets.

arXiv comment8 pages, 10 figures, Submitted to IEEE TGRS, Code available at: https://github.com/kaustubh0mani/BASS-Net

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Advances in Hyperspectral Image Classification: Earth monitoring with statistical learning methods

Cited by in corpus (12)

• Deep learning in remote sensing: a review
• Deep Learning for Hyperspectral Image Classification: An Overview
• Validating Hyperspectral Image Segmentation
• DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification
• Unsupervised Segmentation of Hyperspectral Images Using 3D Convolutional Autoencoders
• Deep-Learning Convolutional Neural Networks for scattered shrub detection with Google Earth Imagery
• Transfer Learning for Segmenting Dimensionally-Reduced Hyperspectral Images
• Hyperspectral Data Augmentation
• Decision Tree Learning with Spatial Modal Logics
• Optimizing CNN-based Hyperspectral Image Classification on FPGAs
• Segmenting Hyperspectral Images Using Spectral-Spatial Convolutional Neural Networks With Training-Time Data Augmentation
• PUNCH: Positive UNlabelled Classification based information retrieval in Hyperspectral images