JL1-CC&QA：扩展JL1-CD基准，增加变化描述和问答
JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering
AI总结：
提出JL1-CC&QA多任务基准，通过变化描述和问答扩展JL1-CD，利用吉林一号卫星图像和三级标注流程，推动遥感变化理解。
摘要：
遥感变化检测（CD）传统上侧重于像素级二值分割，识别变化发生的位置，但不涉及变化的内容和原因。为弥合这一语义鸿沟，我们引入JL1-CC&QA，一个多任务基准，通过两个互补的标注层扩展JL1-CD数据集：变化描述（CC）和变化问答（QA）。该基准基于吉林一号卫星在0.5-0.75米地面采样距离下获取的5,000对双时相图像，包括：(i) JL1-CC，提供17,021条经过质量验证的描述，描述多样化的土地覆盖变化；(ii) JL1-QA，提供20,060个问答对，涵盖八种问题类型，支持对地表变化进行细粒度、交互式的查询。所有标注通过一个三级流程生成，包括多模态大语言模型（LLM）生成、基于视觉的LLM评判和人类专家验证。我们希望JL1-CC&QA作为一个在同一图像集上统一二值变化掩膜、变化描述和面向变化的问答的基准，能够成为社区推进遥感多任务变化理解的宝贵资源。数据集可在https://this https URL获取。
英文摘要：
Remote sensing change detection (CD) traditionally focuses on pixel-level binary segmentation, which identifies where changes occur but neither what nor why. To bridge this semantic gap, we introduce JL1-CC&QA, a multi-task benchmark that extends the JL1-CD dataset with two complementary annotation layers: change captioning (CC) and change question answering (QA). Built upon 5,000 bi-temporal image pairs acquired by the Jilin-1 satellite at 0.5-0.75m ground sample distance, the benchmark comprises: (i) JL1-CC, providing 17,021 quality-verified captions that describe diverse land-cover transformations; and (ii) JL1-QA, offering 20,060 question-answer pairs across eight question types, enabling fine-grained, interactive interrogation of surface changes. All annotations are produced via a three-stage pipeline consisting of multi-modal large language model (LLM) generation, vision-grounded LLM judging, and human expert verification. We hope that JL1-CC&QA, as a benchmark unifying binary change masks, change captions, and change-oriented QA over the same image set, will serve as a valuable resource for the community to advance multi-task change understanding in remote sensing. The dataset is available at https://github.com/circleLZY/JL1-CD.
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。
