KD-RSCC: A Karras Diffusion Framework for Efficient Remote Sensing Change Captioning

Abstract

Remote sensing image change captioning (RSICC) is a challenging task that involves describing surface changes between bitemporal or multitemporal satellite images using natural language. This task requires both fine-grained visual understanding and expressive language generation. Transformer-based and long short-term memory (LSTM)-based models have shown promising results in this domain. However, they may encounter difficulties in generating flexible and diverse captions, particularly when training data are limited or imbalanced. While diffusion models provide richer textual outputs, they are often constrained by long inference times. To address these issues, we propose a novel diffusion-based framework, KD-RSCC, for efficient and expressive remote sensing change captioning. This framework utilizes the Karras sampling method to significantly reduce the number of steps required during inference, while preserving the quality and diversity of the generated captions. In addition, we introduce a large language model (LLM)-based evaluation strategy $\text {G-Eval}_{\text {RSCC}}$ to conduct a more comprehensive assessment of the semantic accuracy, fluency, and linguistic diversity of the generated descriptions. Experimental results demonstrate that KD-RSCC achieves an optimal balance between generation quality and inference speed, enhancing the flexibility and readability of its outputs. The code and supplementary materials are available at https://github.com/Fay-Y/KD_RSCC