Problem
Research questions and friction points this paper is trying to address.
Building Damage Assessment
Vision-Language Model
autoregressive sequence generation
GeBDA: Building Damage Assessment as Text-Based Sequence Prediction
🤖 AI Summary
研究通过使用通用视觉-语言模型进行自回归序列生成，以预测带损伤标签的边界框集合，实现建筑物损伤评估。
📝 Abstract
Conventionally, Building Damage Assessment (BDA) is tackled either with dedicated network architectures or by fine-tuning geospatial image foundation models. In this work, we ask whether a general-purpose Vision-Language Model (VLM) can localize buildings and grade their damage through autoregressive sequence generation alone. We cast BDA as predicting a variable-length set of bounding boxes, each specified by its coordinates and a damage label. Our preliminary implementation, based on the open Gemma model, achieves promising damage mapping results from only bi-temporal satellite images and a suitable text prompt.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Vision-Language Model
autoregressive sequence generation
Building Damage Assessment
🔎 Similar Papers
No similar papers found.
