HomeLREC 2026WorkshopsNAKBANLPlrec2026-ws-nakbanlp-45
Back to NAKBANLP 2026
LREC 2026workshop

NU_Hallucinators at NakbaArchiveClassifier Shared Task: A CLIP-Based Approach for Destruction Detection in Historical Image Archives

Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026

DOI:10.63317/4c5nkazsww8o

Abstract

This paper presents a CLIP-based transfer learning approach for classifying historical archive images in the Nakba Image Classification Shared Task at the Nakba-NLP 2026 Workshop (LREC 2026). The task involves distinguishing images depicting destroyed or damaged infrastructure from those showing intact scenes using a dataset of 2,001 images collected from Instagram posts published by Palestinian content creators and journalists in Gaza between October 2023 and December 2025. Our method employs the CLIP ViT-B/32 visual encoder with selective fine-tuning of the final transformer block and a lightweight classification head. To address class imbalance, we apply focal loss along with standard data augmentation and threshold optimization. Experimental results show that the proposed model outperforms several CNN baselines and achieves an F1-score of 0.877 on the blind test set, securing 4th place in the shared task.

Details

Paper ID
lrec2026-ws-nakbanlp-45
Pages
pp. 285-289
BibKey
hegazy-etal-2026-nu_hallucinators
Editors
Mustafa Jarrar, Mo El-Haj, Amal Haddad, Serin Atiani, Shadi Abudalfa, Terry Regier, Paul Rayson, Khalil Sima’an, Camille Mansour
Publisher
European Language Resources Association (ELRA)
ISSN
N/A
ISBN
N/A
Workshop
Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
Location
Palma, Mallorca, Spain
Date
11 - 16 May 2026

Authors

  • SH

    Salma Khaled Hegazy

  • MR

    Mohamed Ibrahim Ragab

Links