先思后定（ThiFAN-VQA）：一种用于灾后损害评估的两阶段链式思考框架
Think First, Assign Next (ThiFAN-VQA): A Two-stage Chain-of-Thought Framework for Post-Disaster Damage Assessment
AI总结：
ThiFAN-VQA通过两阶段推理框架提升灾后损害评估的准确性与可解释性。
摘要：
及时准确地评估自然灾害后的损害对于有效的应急响应和恢复至关重要。最近基于AI的框架已被开发用于分析由无人机收集的大量高空影像，快速提供可操作的见解。然而，创建和标注用于训练这些模型的数据成本高且耗时，导致数据集在规模和多样性上有限。此外，大多数现有方法依赖于基于传统分类的框架，具有固定的答案空间，限制了其在没有额外数据收集或模型重新训练的情况下提供新信息的能力。使用基于上下文学习（ICL）预训练的生成模型允许灵活且开放的答案空间。然而，这些模型往往生成幻觉输出或产生通用响应，缺乏领域特定的相关性。为了解决这些限制，我们提出了ThiFAN-VQA，一种用于灾难场景的视觉问答（VQA）的两阶段推理框架。ThiFAN-VQA首先使用链式思考（CoT）提示和ICL生成结构化的推理轨迹，以在有限监督下实现可解释的推理。随后的答案选择模块评估生成的响应并分配最连贯且上下文准确的答案，从而有效提高模型性能。通过整合定制的信息检索系统、领域特定提示和推理引导的答案选择，ThiFAN-VQA弥合了零样本和监督方法之间的差距，结合了灵活性与一致性。在FloodNet和RescueNet-VQA、基于无人机的洪水和飓风影响区域的数据集上进行的实验表明，ThiFAN-VQA在真实世界灾后损害评估任务中实现了更高的准确性、可解释性和适应性。
英文摘要：
Timely and accurate assessment of damages following natural disasters is essential for effective emergency response and recovery. Recent AI-based frameworks have been developed to analyze large volumes of aerial imagery collected by Unmanned Aerial Vehicles, providing actionable insights rapidly. However, creating and annotating data for training these models is costly and time-consuming, resulting in datasets that are limited in size and diversity. Furthermore, most existing approaches rely on traditional classification-based frameworks with fixed answer spaces, restricting their ability to provide new information without additional data collection or model retraining. Using pre-trained generative models built on in-context learning (ICL) allows for flexible and open-ended answer spaces. However, these models often generate hallucinated outputs or produce generic responses that lack domain-specific relevance. To address these limitations, we propose ThiFAN-VQA, a two-stage reasoning-based framework for visual question answering (VQA) in disaster scenarios. ThiFAN-VQA first generates structured reasoning traces using chain-of-thought (CoT) prompting and ICL to enable interpretable reasoning under limited supervision. A subsequent answer selection module evaluates the generated responses and assigns the most coherent and contextually accurate answer, effectively improve the model performance. By integrating a custom information retrieval system, domain-specific prompting, and reasoning-guided answer selection, ThiFAN-VQA bridges the gap between zero-shot and supervised methods, combining flexibility with consistency. Experiments on FloodNet and RescueNet-VQA, UAV-based datasets from flood- and hurricane-affected regions, demonstrate that ThiFAN-VQA achieves superior accuracy, interpretability, and adaptability for real-world post-disaster damage assessment tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
