3D CNN with Localized Residual Connections for Hyperspectral Image Classification

TL;DR

This paper introduces a novel 3D CNN with localized residual connections for hyperspectral image classification, improving feature extraction by combining multi-stage residuals, and demonstrates superior performance on benchmark datasets.

Contribution

The paper proposes a new 3D CNN architecture with localized residual connections that effectively integrates features from multiple stages for hyperspectral image classification.

Findings

Outperforms state-of-the-art methods on Pavia datasets

Residual connections improve feature integration and classification accuracy

Model achieves significant performance gains over existing approaches

Abstract

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.