AI 中文总结
针对现有遥感灾害变化描述方法的级联事实错误问题，提出EchoChange扩散语言模型，经实验在RSCC基准上优于各类基线
AI 中文摘要
双时相遥感灾害变化描述通常需要识别前后事件场景中稀疏且空间局部的变化，并将其转化为连贯、事实性的描述。然而，现有的变化描述方法始终遵循自回归解码范式生成描述，因此对变化对象、事件或空间关系的早期误读会成为后续文本的不可逆前提，将视觉歧义放大为级联事实错误。为解决这一局限，我们提出EchoChange，这是一种多模态离散扩散语言模型，将变化描述建模为迭代的掩码标记去噪而非从左到右的生成。通过在图像对的条件下反复修正整个描述，EchoChange能够重新考虑不确定内容并修正不完善的中间预测。我们进一步引入草稿感知双遍训练、渐进式掩码课程以及置信度引导的重掩蔽，使训练与迭代推理对齐。在RSCC基准上的大量实验表明，EchoChange在词汇和语义指标上均显著优于通用型和遥感专用型基线。EchoChange项目可访问此https URL
英文摘要
Bi-temporal remote-sensing disaster change captioning often needs to identify sparse and spatially localized changes across large pre- and post-event scenes and then translate them into coherent, factual descriptions. However, existing change captioning methods always follow an autoregressive decoding paradigm to generate the change description and thus an early misinterpretation of the changed object, event, or spatial relation becomes an irreversible premise for subsequent text, amplifying visual ambiguity into cascading factual errors. To address this limitation, we propose EchoChange, a multimodal discrete diffusion language model that formulates change captioning as iterative masked-token denoising rather than left-to-right generation. By repeatedly revising the entire caption while conditioning on the image pair, EchoChange can reconsider uncertain content and correct imperfect intermediate predictions. We further introduce draft-aware dual-pass training, a progressive masking curriculum, and confidence-guided remasking to align training with iterative inference. Extensive experiments on the RSCC benchmark show that EchoChange substantially outperforms both general-purpose and remote-sensing-specific baselines across lexical and semantic metrics. The EchoChange Project is at https://sundongwei.github.io/EchoChange_Project/
