Boosting Hyperspectral Image Classification with Gate-Shift-Fuse Mechanisms in a Novel CNN-Transformer Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guerri, Mohamed Fadhlallah, Distante, Cosimo, Spagnolo, Paolo, Bougourzi, Fares, Taleb-Ahmed, Abdelmalik
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917793282129920
author Guerri, Mohamed Fadhlallah
Distante, Cosimo
Spagnolo, Paolo
Bougourzi, Fares
Taleb-Ahmed, Abdelmalik
author_facet Guerri, Mohamed Fadhlallah
Distante, Cosimo
Spagnolo, Paolo
Bougourzi, Fares
Taleb-Ahmed, Abdelmalik
contents During the process of classifying Hyperspectral Image (HSI), every pixel sample is categorized under a land-cover type. CNN-based techniques for HSI classification have notably advanced the field by their adept feature representation capabilities. However, acquiring deep features remains a challenge for these CNN-based methods. In contrast, transformer models are adept at extracting high-level semantic features, offering a complementary strength. This paper's main contribution is the introduction of an HSI classification model that includes two convolutional blocks, a Gate-Shift-Fuse (GSF) block and a transformer block. This model leverages the strengths of CNNs in local feature extraction and transformers in long-range context modelling. The GSF block is designed to strengthen the extraction of local and global spatial-spectral features. An effective attention mechanism module is also proposed to enhance the extraction of information from HSI cubes. The proposed method is evaluated on four well-known datasets (the Indian Pines, Pavia University, WHU-WHU-Hi-LongKou and WHU-Hi-HanChuan), demonstrating that the proposed framework achieves superior results compared to other models.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14120
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boosting Hyperspectral Image Classification with Gate-Shift-Fuse Mechanisms in a Novel CNN-Transformer Approach
Guerri, Mohamed Fadhlallah
Distante, Cosimo
Spagnolo, Paolo
Bougourzi, Fares
Taleb-Ahmed, Abdelmalik
Computer Vision and Pattern Recognition
During the process of classifying Hyperspectral Image (HSI), every pixel sample is categorized under a land-cover type. CNN-based techniques for HSI classification have notably advanced the field by their adept feature representation capabilities. However, acquiring deep features remains a challenge for these CNN-based methods. In contrast, transformer models are adept at extracting high-level semantic features, offering a complementary strength. This paper's main contribution is the introduction of an HSI classification model that includes two convolutional blocks, a Gate-Shift-Fuse (GSF) block and a transformer block. This model leverages the strengths of CNNs in local feature extraction and transformers in long-range context modelling. The GSF block is designed to strengthen the extraction of local and global spatial-spectral features. An effective attention mechanism module is also proposed to enhance the extraction of information from HSI cubes. The proposed method is evaluated on four well-known datasets (the Indian Pines, Pavia University, WHU-WHU-Hi-LongKou and WHU-Hi-HanChuan), demonstrating that the proposed framework achieves superior results compared to other models.
title Boosting Hyperspectral Image Classification with Gate-Shift-Fuse Mechanisms in a Novel CNN-Transformer Approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.14120