HCMUS_TheFangs at NakbaArchiveClassifier Shared Task: Foundation Models and Advanced Training Strategies for Conflict Damage Classification

Duy Minh Dao Sy, Trung Kiet Huynh, Nguyen Chi Tran, Phu Quy Nguyen Lam, Phu Hoa Pham


Abstract
We present our system for the NakbaArchiveClassifier shared task at Nakba-NLP 2026, which requires classifying Instagram images from Gaza as showing destroyed or damaged infrastructure versus intact surroundings. Working with a small, imbalanced dataset (1,400 training images; 1.83:1 class ratio), we conduct a systematic empirical study of six model-training combinations spanning five architecture families: standard CNNs (EfficientNet-B4), self-supervised ViTs (DINOv2-ViT-L), hybrid multi-axis Transformers (MaxViT-Base), masked-image-modelling ViTs (EVA-02-Base), and large-kernel CNNs (UniRepLKNet). For our best performing configuration–MaxViT-Base with focal loss, MixUp, and a rich geometric augmentation pipeline–we provide a detailed component analysis. Our system achieves a macro F1 of 0.899 on the public test set, ranking 1st on the competition leaderboard. We additionally report findings from novel experiments including a Kolmogorov-Arnold Network (KAN) classification head and VLM-regularized training with BLIP-2-generated captions, offering insights into what does and does not transfer to conflict-domain imagery under severe data scarcity.
Anthology ID:
2026.nakbanlp-1.15
Volume:
Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Mustafa Jarrar, Mo El-Haj, Amal Haddad, Serin Atiani, Shadi Abudalfa, Terry Regier, Paul Rayson, Khalil Sima’an, Camille Mansour
Venues:
NakbaNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
121–127
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-nakbanlp-15
DOI:
10.63317/26tv58oaqfc4
Bibkey:
Cite (ACL):
Duy Minh Dao Sy, Trung Kiet Huynh, Nguyen Chi Tran, Phu Quy Nguyen Lam, and Phu Hoa Pham. 2026. HCMUS_TheFangs at NakbaArchiveClassifier Shared Task: Foundation Models and Advanced Training Strategies for Conflict Damage Classification. In Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026, pages 121–127, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
HCMUS_TheFangs at NakbaArchiveClassifier Shared Task: Foundation Models and Advanced Training Strategies for Conflict Damage Classification (Dao Sy et al., NakbaNLP 2026)
Copy Citation: