JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering
For researchers in remote sensing change understanding, this benchmark enables multi-task learning and evaluation, but it is an incremental contribution as it extends an existing dataset with new annotation layers.
The paper introduces JL1-CC&QA, a multi-task benchmark extending the JL1-CD dataset with change captioning and question answering annotations, comprising 17,021 captions and 20,060 QA pairs over 5,000 bi-temporal image pairs. It aims to bridge the semantic gap in remote sensing change detection by providing complementary annotations beyond binary segmentation.
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.