遥感鲁棒变化描述：SECOND-CC数据集与MModalCC框架
Robust Change Captioning in Remote Sensing: SECOND-CC Dataset and MModalCC Framework
AI总结：
针对现有遥感变化描述方法在光照差异等挑战下表现不佳及数据缺陷问题，提出含6041对图像对的SECOND-CC数据集和MModalCC多模态框架，该框架整合语义与视觉数据，实验显示其在BLEU4和CIDEr得分上优于现有方法。
摘要：
遥感变化描述（RSICC）旨在用自然语言描述双时相图像间的变化。现有方法常因光照差异、视角变化、模糊效应等挑战失效，导致描述不准确，尤其在无变化区域。此外，不同空间分辨率获取的图像及配准误差易影响描述。为解决这些问题，我们引入SECOND-CC，这是一个包含高分辨率RGB图像对、语义分割图和多样真实场景的新型RSICC数据集，含6041对双时相遥感图像和30205句描述图像差异的句子。同时，我们提出MModalCC多模态框架，通过跨模态交叉注意力（CMCA）和多模态门控交叉注意力（MGCA）等先进注意力机制整合语义与视觉数据。详细消融研究和注意力可视化进一步证明其有效性及应对RSICC挑战的能力。综合实验表明，MModalCC优于RSICCformer、Chg2Cap和PSNet等现有RSICC方法，BLEU4得分提升+4.6%，CIDEr得分提升+9.6%。我们将公开数据集和代码库以促进未来研究，网址为https://github.com/ChangeCapsInRS/SecondCC
英文摘要：
Remote sensing change captioning (RSICC) aims to describe changes between bitemporal images in natural language. Existing methods often fail under challenges like illumination differences, viewpoint changes, blur effects, leading to inaccuracies, especially in no-change regions. Moreover, the images acquired at different spatial resolutions and have registration errors tend to affect the captions. To address these issues, we introduce SECOND-CC, a novel RSICC dataset featuring high-resolution RGB image pairs, semantic segmentation maps, and diverse real-world scenarios. SECOND-CC which contains 6,041 pairs of bitemporal RS images and 30,205 sentences describing the differences between images. Additionally, we propose MModalCC, a multimodal framework that integrates semantic and visual data using advanced attention mechanisms, including Cross-Modal Cross Attention (CMCA) and Multimodal Gated Cross Attention (MGCA). Detailed ablation studies and attention visualizations further demonstrate its effectiveness and ability to address RSICC challenges. Comprehensive experiments show that MModalCC outperforms state-of-the-art RSICC methods, including RSICCformer, Chg2Cap, and PSNet with +4.6% improvement on BLEU4 score and +9.6% improvement on CIDEr score. We will make our dataset and codebase publicly available to facilitate future research at https://github.com/ChangeCapsInRS/SecondCC
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。
