Gam-UNet for Semantic Segmentation

Rahma Aloui, Pranav Martini, Pandu Devarakota, Apurva Gala, Shishir Shah

2025

Abstract

Accurate delineation of critical features, such as salt boundaries in seismic imaging and fine structures in medical images, is essential for effective analysis and decision-making. Traditional convolutional neural networks (CNNs) often face difficulties in handling complex data due to variations in scale, orientation, and noise. These limitations become particularly evident during the transition from proof-of-concept to real-world deployment, where models must perform consistently under diverse conditions. To address these challenges, we propose GAM-UNet, an advanced segmentation architecture that integrates learnable Gabor filters for enhanced edge detection, SCSE blocks for feature refinement, and multi-scale fusion within the U-Net framework. This approach improves feature extraction across varying scales and orientations. Trained using a combined Binary Cross-Entropy and Dice loss function, GAM-UNet demonstrates superior segmentation accuracy and continuity, outperforming existing U-Net variants across diverse datasets.

Paper Citation

in Harvard Style

Aloui R., Martini P., Devarakota P., Gala A. and Shah S. (2025). Gam-UNet for Semantic Segmentation. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 524-531. DOI: 10.5220/0013182000003912

in Bibtex Style

@conference{visapp25,
author={Rahma Aloui and Pranav Martini and Pandu Devarakota and Apurva Gala and Shishir Shah},
title={Gam-UNet for Semantic Segmentation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={524-531},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013182000003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Gam-UNet for Semantic Segmentation
SN - 978-989-758-728-3
AU - Aloui R.
AU - Martini P.
AU - Devarakota P.
AU - Gala A.
AU - Shah S.
PY - 2025
SP - 524
EP - 531
DO - 10.5220/0013182000003912
PB - SciTePress