cd /news/machine-learning/hope-at-nakbaarchiveclassifier-share… · home topics machine-learning article
[ARTICLE · art-86805] src=aclanthology.org ↗ pub= topic=machine-learning verified=true sentiment=· neutral

"Hope" at NakbaArchiveClassifier Shared Task: Transfer Learning-Based CNN Models for Infrastructure Damage Detection

Team Hope's ResNet34 model, fine-tuned with ImageNet pretrained weights for 25 epochs using the Adam optimizer and a learning rate of 1e-4, achieved 81% accuracy on the NakbaArchiveClassifier Shared Task at Nakba-NLP 2026, outperforming other tested architectures including ResNet50 and EfficientNet-B0. The system, developed by Lojien AlKhidir and HebaTalla Abdelhady, classified 2,001 Instagram images into destruction and not_destruction categories, demonstrating that moderate-depth CNNs can generalize effectively in low-resource visual classification tasks.

read2 min views20 publishedJul 24, 2026
Abstract

This paper describes Team Hope’s system for the NakbaArchiveClassifier Shared Task at Nakba-NLP 2026. The task focuses on binary classification of social media images into two categories: destruction and not_destruction. We evaluated multiple convolutional neural network architectures using transfer learning, including ResNet34, ResNet50, EfficientNet-B0, and a fine-tuned ResNet34 variant with staged training. All models were initialized with ImageNet pretrained weights and fine-tuned on the provided dataset of 2,001 images. The dataset is moderately imbalanced and contains visually diverse Instagram images depicting intact and damaged infrastructure. Our best-performing model, ResNet34 trained for 25 epochs with Adam optimizer and a learning rate of 1e-4, achieved 81% accuracy on the evaluation platform. We provide a comparative analysis of the tested architectures and discuss the impact of model depth, training duration, and class imbalance. Given the political and ethical sensitivity of the dataset, we also include a discussion of responsible AI considerations and potential limitations. Our findings suggest that moderate-depth architectures can generalize effectively in low-resource, contextually complex visual classification tasks.- Anthology ID:

- 2026.nakbanlp-1.25
- Volume:
[Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026](/volumes/2026.nakbanlp-1/)- 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](/venues/nakbanlp/)|[WS](/venues/ws/)- SIG:
- Publisher:
- ELRA Language Resources Association (ELRA)
- Note:
- Pages:
  • 187–190
- Language:
- External URL:
[https://lrec.elra.info/lrec2026-ws-nakbanlp-25](https://lrec.elra.info/lrec2026-ws-nakbanlp-25)- DOI:
[10.63317/233j9kgmifw4](https://doi.org/10.63317/233j9kgmifw4)- Cite (ACL):
── more in #machine-learning 4 stories · sorted by recency
── more on @team hope 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/hope-at-nakbaarchive…] indexed:0 read:2min 2026-07-24 ·