@inproceedings{mohamed-etal-2026-overfit,
title = "No Overfit at {N}akba{A}rchive{C}lassifier Shared Task: A Swin Transformer-Based System for Destruction Image Classification",
author = "Mohamed, Mohamed Fathy and
Abd El-Mageed, Samar Mahmoud and
Mohamed, Ensaf",
editor = "Jarrar, Mustafa and
El-Haj, Mo and
Haddad, Amal and
Atiani, Serin and
Abudalfa, Shadi and
Regier, Terry and
Rayson, Paul and
Sima{'}an, Khalil and
Mansour, Camille",
booktitle = "Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nakbanlp-1.22/",
doi = "10.63317/28o7zedpovh7",
pages = "171--176",
abstract = "Automated destruction identification from visual data plays a critical role in large-scale documentation, humanitarian analysis, and digital archiving of conflict-related events. Within this context, the Nakba-NLP 2026 Workshop introduced a shared task aimed at training and evaluating a binary image classification model to distinguish between destroyed or damaged infrastructure and intact infrastructure. However, the limited dataset size and the visual variability of real-world scenes make this task particularly challenging. This work presents a Swin Transformer{--}based framework tailored for destruction image classification. The proposed model employs a hierarchical Swin Transformer backbone for robust feature extraction, followed by a multi-layer perceptron classifier for decision-making. To address the limited data issue, transfer learning and a customized training strategy are applied to adapt the model effectively without full end-to-end retraining. Furthermore, a semi-supervised data expansion approach is utilized to enlarge the training set from 1,400 to 10,000 images, improving model generalization and robustness. Experimental results on the official blind test set demonstrate strong performance, achieving an F1-score of 86.55{\%} and an accuracy of 87.81{\%}, ranking 5th in the shared task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-etal-2026-overfit">
<titleInfo>
<title>No Overfit at NakbaArchiveClassifier Shared Task: A Swin Transformer-Based System for Destruction Image Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Fathy</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Abd El-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ensaf</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serin</namePart>
<namePart type="family">Atiani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Abudalfa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Regier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Sima’an</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated destruction identification from visual data plays a critical role in large-scale documentation, humanitarian analysis, and digital archiving of conflict-related events. Within this context, the Nakba-NLP 2026 Workshop introduced a shared task aimed at training and evaluating a binary image classification model to distinguish between destroyed or damaged infrastructure and intact infrastructure. However, the limited dataset size and the visual variability of real-world scenes make this task particularly challenging. This work presents a Swin Transformer–based framework tailored for destruction image classification. The proposed model employs a hierarchical Swin Transformer backbone for robust feature extraction, followed by a multi-layer perceptron classifier for decision-making. To address the limited data issue, transfer learning and a customized training strategy are applied to adapt the model effectively without full end-to-end retraining. Furthermore, a semi-supervised data expansion approach is utilized to enlarge the training set from 1,400 to 10,000 images, improving model generalization and robustness. Experimental results on the official blind test set demonstrate strong performance, achieving an F1-score of 86.55% and an accuracy of 87.81%, ranking 5th in the shared task.</abstract>
<identifier type="citekey">mohamed-etal-2026-overfit</identifier>
<identifier type="doi">10.63317/28o7zedpovh7</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.22/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>171</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T No Overfit at NakbaArchiveClassifier Shared Task: A Swin Transformer-Based System for Destruction Image Classification
%A Mohamed, Mohamed Fathy
%A Abd El-Mageed, Samar Mahmoud
%A Mohamed, Ensaf
%Y Jarrar, Mustafa
%Y El-Haj, Mo
%Y Haddad, Amal
%Y Atiani, Serin
%Y Abudalfa, Shadi
%Y Regier, Terry
%Y Rayson, Paul
%Y Sima’an, Khalil
%Y Mansour, Camille
%S Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F mohamed-etal-2026-overfit
%X Automated destruction identification from visual data plays a critical role in large-scale documentation, humanitarian analysis, and digital archiving of conflict-related events. Within this context, the Nakba-NLP 2026 Workshop introduced a shared task aimed at training and evaluating a binary image classification model to distinguish between destroyed or damaged infrastructure and intact infrastructure. However, the limited dataset size and the visual variability of real-world scenes make this task particularly challenging. This work presents a Swin Transformer–based framework tailored for destruction image classification. The proposed model employs a hierarchical Swin Transformer backbone for robust feature extraction, followed by a multi-layer perceptron classifier for decision-making. To address the limited data issue, transfer learning and a customized training strategy are applied to adapt the model effectively without full end-to-end retraining. Furthermore, a semi-supervised data expansion approach is utilized to enlarge the training set from 1,400 to 10,000 images, improving model generalization and robustness. Experimental results on the official blind test set demonstrate strong performance, achieving an F1-score of 86.55% and an accuracy of 87.81%, ranking 5th in the shared task.
%R 10.63317/28o7zedpovh7
%U https://aclanthology.org/2026.nakbanlp-1.22/
%U https://doi.org/10.63317/28o7zedpovh7
%P 171-176
Markdown (Informal)
[No Overfit at NakbaArchiveClassifier Shared Task: A Swin Transformer-Based System for Destruction Image Classification](https://aclanthology.org/2026.nakbanlp-1.22/) (Mohamed et al., NakbaNLP 2026)
ACL