遥感视觉问答中答案-证据一致性的基准测试
Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering
AI总结：
该研究针对遥感视觉问答中答案与证据一致性评估的缺失问题，提出AESP协议并构建G-RSVQA基准，实验发现7个模型在三类问题中均存在证据支持失败的情况。
摘要：
在基于证据的遥感视觉问答中，模型会生成文本答案并识别图像中相关对象作为证据。现有评估仅衡量答案正确性和定位质量，未直接评估答案与证据的一致性。我们提出答案-证据支持协议（AESP），通过证据支持度评估该一致性，即证据是否支持模型自身的答案。AESP针对存在、计数、比较类问题应用特定任务规则。我们进一步构建了基于证据的遥感视觉问答基准（G-RSVQA），包含15027个样本，涵盖问题、参考答案及所有相关对象级标注。对7个基于证据的视觉-语言模型的实验显示，三类问题均存在证据支持失败的情况：在证据评估子集里，高达50.82%的正确答案未被提供的证据支持。
英文摘要：
In grounded remote sensing visual question answering, a model produces a textual answer and identifies relevant objects in the image as grounding evidence. Existing evaluations measure answer correctness and localization quality, but do not directly assess answer-grounding consistency. We propose the Answer-Evidence Support Protocol (AESP) to assess this consistency through evidence support: whether the grounding evidence supports the model's own answer. AESP applies task-specific rules to existence, counting, and comparison questions. We further construct the Grounded Remote Sensing Visual Question Answering (G-RSVQA) benchmark, containing 15,027 samples with questions, reference answers, and all related object-level annotations. Experiments on seven grounded vision--language models reveal failures of evidence support across all three question types. Up to 50.82% of correct answers in the evidence evaluation subset are not supported by the provided grounding evidence.
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。
