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

Anirban Santara, Kaustubh Mani, Pranoot Hatwar, Ankit Singh, Ankur Garg, Kirti Padia, Pabitra Mitra
2017 IEEE Transactions on Geoscience and Remote Sensing  
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
more » ... er of training data. The method is found to outperform the highest reported accuracies on popular hyperspectral image data sets.
doi:10.1109/tgrs.2017.2705073 fatcat:nkg5lzfly5gpxd33drr6jnspm4