Evaluation of Attention Mechanisms in U-Net Architectures for Semantic Segmentation of Brazilian Rock Art Petroglyphs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Melo, Leonardi, Gustavo, Luís, Magalhães, Dimmy, Vieira, Lucciani, Araújo, Mauro
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915619256926208
author Melo, Leonardi
Gustavo, Luís
Magalhães, Dimmy
Vieira, Lucciani
Araújo, Mauro
author_facet Melo, Leonardi
Gustavo, Luís
Magalhães, Dimmy
Vieira, Lucciani
Araújo, Mauro
contents This study presents a comparative analysis of three U-Net-based architectures for semantic segmentation of rock art petroglyphs from Brazilian archaeological sites. The investigated architectures were: (1) BEGL-UNet with Border-Enhanced Gaussian Loss function; (2) Attention-Residual BEGL-UNet, incorporating residual blocks and gated attention mechanisms; and (3) Spatial Channel Attention BEGL-UNet, which employs spatial-channel attention modules based on Convolutional Block Attention Module. All implementations employed the BEGL loss function combining binary cross-entropy with Gaussian edge enhancement. Experiments were conducted on images from the Poço da Bebidinha Archaeological Complex, Piauí, Brazil, using 5-fold cross-validation. Among the architectures, Attention-Residual BEGL-UNet achieved the best overall performance with Dice Score of 0.710, validation loss of 0.067, and highest recall of 0.854. Spatial Channel Attention BEGL-UNet obtained comparable performance with DSC of 0.707 and recall of 0.857. The baseline BEGL-UNet registered DSC of 0.690. These results demonstrate the effectiveness of attention mechanisms for archaeological heritage digital preservation, with Dice Score improvements of 2.5-2.9% over the baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluation of Attention Mechanisms in U-Net Architectures for Semantic Segmentation of Brazilian Rock Art Petroglyphs
Melo, Leonardi
Gustavo, Luís
Magalhães, Dimmy
Vieira, Lucciani
Araújo, Mauro
Computer Vision and Pattern Recognition
I.4.6; I.2.10
This study presents a comparative analysis of three U-Net-based architectures for semantic segmentation of rock art petroglyphs from Brazilian archaeological sites. The investigated architectures were: (1) BEGL-UNet with Border-Enhanced Gaussian Loss function; (2) Attention-Residual BEGL-UNet, incorporating residual blocks and gated attention mechanisms; and (3) Spatial Channel Attention BEGL-UNet, which employs spatial-channel attention modules based on Convolutional Block Attention Module. All implementations employed the BEGL loss function combining binary cross-entropy with Gaussian edge enhancement. Experiments were conducted on images from the Poço da Bebidinha Archaeological Complex, Piauí, Brazil, using 5-fold cross-validation. Among the architectures, Attention-Residual BEGL-UNet achieved the best overall performance with Dice Score of 0.710, validation loss of 0.067, and highest recall of 0.854. Spatial Channel Attention BEGL-UNet obtained comparable performance with DSC of 0.707 and recall of 0.857. The baseline BEGL-UNet registered DSC of 0.690. These results demonstrate the effectiveness of attention mechanisms for archaeological heritage digital preservation, with Dice Score improvements of 2.5-2.9% over the baseline.
title Evaluation of Attention Mechanisms in U-Net Architectures for Semantic Segmentation of Brazilian Rock Art Petroglyphs
topic Computer Vision and Pattern Recognition
I.4.6; I.2.10
url https://arxiv.org/abs/2511.11959