Enhancing LULC Classification with Attention-Based Fusion of Handcrafted and Deep Features

Vian Ahmed, Khaled Jouini, Ouajdi Korbaa

2025

Abstract

Satellite imagery provides a unique perspective of the Earth’s surface, pivotal for applications like environmental monitoring and urban planning. Despite significant advancements, analyzing satellite imagery remains challenging due to complex and variable land cover patterns. Traditional handcrafted descriptors like Scale-Invariant Feature Transform (SIFT) excel at capturing local features but often fail to capture the global context. Conversely, Convolutional Neural Networks (CNNs) excel at capturing rich contextual information but may miss crucial local features due to limitations in capturing small and subtle spatial arrangements. Most existing Land Use and Land Cover (LULC) classification approaches heavily rely on fine-tuning large pretrained models. While this remains a powerful tool, this paper explores alternative strategies by leveraging the complementary strengths of handcrafted and CNN-learned features. Specifically, we investigate and compare three fusion strategies: (i) early fusion, where handcrafted and CNN-learned features are merged at the input level; (ii) late fusion, where attention mechanisms dynamically integrate salient features from both CNN and SIFT modalities; and (iii) mid-level fusion, where attention is used to generate two feature maps: one prioritizing global context and another, weighted by SIFT features, emphasizing local details. Experiments on the real-world EuroSAT dataset demonstrate that these fusion approaches exhibit varying levels of effectiveness and that a well-chosen fusion strategy not only substantially outperforms the underlying methods used separately but also offers an interesting alternative to solely relying on fine-tuning pre-trained large models.

Paper Citation

in Harvard Style

Ahmed V., Jouini K. and Korbaa O. (2025). Enhancing LULC Classification with Attention-Based Fusion of Handcrafted and Deep Features. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 69-78. DOI: 10.5220/0013098500003890

in Bibtex Style

@conference{icaart25,
author={Vian Ahmed and Khaled Jouini and Ouajdi Korbaa},
title={Enhancing LULC Classification with Attention-Based Fusion of Handcrafted and Deep Features},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={69-78},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013098500003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Enhancing LULC Classification with Attention-Based Fusion of Handcrafted and Deep Features
SN - 978-989-758-737-5
AU - Ahmed V.
AU - Jouini K.
AU - Korbaa O.
PY - 2025
SP - 69
EP - 78
DO - 10.5220/0013098500003890
PB - SciTePress