3D CNN with Localized Residual Connections for Hyperspectral Image Classification
This work addresses the problem of improving classification accuracy in hyperspectral imaging, which is important for remote sensing applications, but it appears incremental as it builds on existing CNN and residual connection techniques.
The paper tackles hyperspectral image classification by proposing a 3D CNN with localized residual connections, which outperforms existing state-of-the-art methods on datasets like Pavia University and Pavia Center.
In this paper we propose a novel 3D CNN network with localized residual connections for hyperspectral image classification. Our work chalks a comparative study with the existing methods employed for abstracting deeper features and propose a model which incorporates residual features from multiple stages in the network. The proposed architecture processes individual spatiospectral feature rich cubes from hyperspectral images through 3D convolutional layers. The residual connections result in improved performance due to assimilation of both low-level and high-level features. We conduct experiments over Pavia University and Pavia Center dataset for performance analysis. We compare our method with two recent state-of-the-art methods for hyperspectral image classification method. The proposed network outperforms the existing approaches by a good margin.