Gated-Attention Feature-Fusion Based Framework for Poverty Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ramzan, Muhammad Umer, Khaddim, Wahab, Rana, Muhammad Ehsan, Ali, Usman, Ali, Manohar, Hassan, Fiaz ul, Mehmood, Fatima
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917852006580224
author Ramzan, Muhammad Umer
Khaddim, Wahab
Rana, Muhammad Ehsan
Ali, Usman
Ali, Manohar
Hassan, Fiaz ul
Mehmood, Fatima
author_facet Ramzan, Muhammad Umer
Khaddim, Wahab
Rana, Muhammad Ehsan
Ali, Usman
Ali, Manohar
Hassan, Fiaz ul
Mehmood, Fatima
contents This research paper addresses the significant challenge of accurately estimating poverty levels using deep learning, particularly in developing regions where traditional methods like household surveys are often costly, infrequent, and quickly become outdated. To address these issues, we propose a state-of-the-art Convolutional Neural Network (CNN) architecture, extending the ResNet50 model by incorporating a Gated-Attention Feature-Fusion Module (GAFM). Our architecture is designed to improve the model's ability to capture and combine both global and local features from satellite images, leading to more accurate poverty estimates. The model achieves a 75% R2 score, significantly outperforming existing leading methods in poverty mapping. This improvement is due to the model's capacity to focus on and refine the most relevant features, filtering out unnecessary data, which makes it a powerful tool for remote sensing and poverty estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19690
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gated-Attention Feature-Fusion Based Framework for Poverty Prediction
Ramzan, Muhammad Umer
Khaddim, Wahab
Rana, Muhammad Ehsan
Ali, Usman
Ali, Manohar
Hassan, Fiaz ul
Mehmood, Fatima
Computer Vision and Pattern Recognition
Computers and Society
Machine Learning
This research paper addresses the significant challenge of accurately estimating poverty levels using deep learning, particularly in developing regions where traditional methods like household surveys are often costly, infrequent, and quickly become outdated. To address these issues, we propose a state-of-the-art Convolutional Neural Network (CNN) architecture, extending the ResNet50 model by incorporating a Gated-Attention Feature-Fusion Module (GAFM). Our architecture is designed to improve the model's ability to capture and combine both global and local features from satellite images, leading to more accurate poverty estimates. The model achieves a 75% R2 score, significantly outperforming existing leading methods in poverty mapping. This improvement is due to the model's capacity to focus on and refine the most relevant features, filtering out unnecessary data, which makes it a powerful tool for remote sensing and poverty estimation.
title Gated-Attention Feature-Fusion Based Framework for Poverty Prediction
topic Computer Vision and Pattern Recognition
Computers and Society
Machine Learning
url https://arxiv.org/abs/2411.19690