# 3D/2D regularized CNN feature hierarchy for Hyperspectral image classification

Source: [3D/2D regularized CNN feature hierarchy for Hyperspectral image classification](<https://www.sota2.com/research/paper/68fa69d21e209131cea2465d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:09:38.543Z

Authors: Muhammad Ahmad, Manuel Mazzara, Salvatore Distefano

Published: 2021-04-25T11:26:56.000Z

## Abstract

Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Several regularization techniques have been used to overcome the aforesaid issues. However, sometimes models learn to predict the samples extremely confidently which is not good from a generalization point of view. Therefore, this paper proposed an idea to enhance the generalization performance of a hybrid CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that in improving generalization performance, label smoothing also improves model calibration which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation which reveals improved generalization performance, statistical significance, and computational complexity as compared to the state-of-the-art models. The code will be made available at https://github.com/mahmad00.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.12136>)

[PDF](<https://arxiv.org/pdf/2104.12136.pdf>)