遥感变化字幕生成：向SAT-Cap演进——一种单阶段Transformer方法
Change Captioning in Remote Sensing: Evolution to SAT-Cap -- A Single-Stage Transformer Approach
AI总结：
针对现有遥感变化字幕方法计算量大、目标描述细节不足的问题，提出单阶段Transformer模型SAT-Cap，通过空间-通道注意力编码器和余弦相似度融合模块提升性能，在两个基准数据集上超越现有最优方法。
摘要：
变化字幕生成已成为准确描述多时相遥感数据中变化的关键技术，为通过自然语言监测地球动态提供了直观途径。然而，现有变化字幕生成方法面临两大核心挑战：多阶段融合策略导致计算需求高，且单幅图像语义提取能力有限致使目标描述细节不足。为解决这些问题，我们提出基于Transformer模型的SAT-Cap，采用单阶段特征融合用于遥感变化字幕生成。具体而言，SAT-Cap整合了空间-通道注意力编码器、差异引导融合模块以及字幕解码器。与需要在Transformer编码器和融合模块中进行多阶段融合的典型模型相比，SAT-Cap仅使用一个简单的基于余弦相似度的融合模块进行信息整合，降低了模型架构的复杂度。通过在空间-通道注意力编码器中联合建模空间与通道信息，我们的方法显著提升了模型从多时相遥感图像中提取目标语义信息的能力。大量实验验证了SAT-Cap的有效性，在LEVIR-CC数据集上CIDEr得分达140.23%，在DUBAI-CC数据集上达97.74%，超越了当前最优方法。代码和预训练模型将公开发布。
英文摘要：
Change captioning has become essential for accurately describing changes in multi-temporal remote sensing data, providing an intuitive way to monitor Earth's dynamics through natural language. However, existing change captioning methods face two key challenges: high computational demands due to multistage fusion strategy, and insufficient detail in object descriptions due to limited semantic extraction from individual images. To solve these challenges, we propose SAT-Cap based on the transformers model with a single-stage feature fusion for remote sensing change captioning. In particular, SAT-Cap integrates a Spatial-Channel Attention Encoder, a Difference-Guided Fusion module, and a Caption Decoder. Compared to typical models that require multi-stage fusion in transformer encoder and fusion module, SAT-Cap uses only a simple cosine similarity-based fusion module for information integration, reducing the complexity of the model architecture. By jointly modeling spatial and channel information in Spatial-Channel Attention Encoder, our approach significantly enhances the model's ability to extract semantic information from objects in multi-temporal remote sensing images. Extensive experiments validate the effectiveness of SAT-Cap, achieving CIDEr scores of 140.23% on the LEVIR-CC dataset and 97.74% on the DUBAI-CC dataset, surpassing current state-of-the-art methods. The code and pre-trained models will be available online.
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。
