DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes
This addresses the problem of developing robust vision-language models for disaster response practitioners, though it is incremental as it builds on existing VQA methods by applying them to a new domain-specific dataset.
The paper tackles the lack of a benchmark for Visual Question Answering (VQA) in disaster response by introducing DisasterVQA, a dataset with 1,395 images and 4,405 question-answer pairs, and finds that models perform well on binary questions but struggle with fine-grained reasoning, especially for underrepresented scenarios.
Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage assessment and response. While Visual Question Answering (VQA) has shown strong performance in general-purpose domains, its suitability for the complex and safety-critical reasoning required in disaster response remains unclear. We introduce DisasterVQA, a benchmark dataset designed for perception and reasoning in crisis contexts. DisasterVQA consists of 1,395 real-world images and 4,405 expert-curated question-answer pairs spanning diverse events such as floods, wildfires, and earthquakes. Grounded in humanitarian frameworks including FEMA ESF and OCHA MIRA, the dataset includes binary, multiple-choice, and open-ended questions covering situational awareness and operational decision-making tasks. We benchmark seven state-of-the-art vision-language models and find performance variability across question types, disaster categories, regions, and humanitarian tasks. Although models achieve high accuracy on binary questions, they struggle with fine-grained quantitative reasoning, object counting, and context-sensitive interpretation, particularly for underrepresented disaster scenarios. DisasterVQA provides a challenging and practical benchmark to guide the development of more robust and operationally meaningful vision-language models for disaster response. The dataset is publicly available at https://zenodo.org/records/18267770.