KD-RSCC: A Karras Diffusion Framework for Efficient Remote Sensing Change Captioning
- 10 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
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_RSCCKeywords
Funding Information
- National Natural Science Foundation of China (62101052)
- Fundamental Research Funds for the Central Universities (2024JX068, 2024JJ040, 2024JJ039)
This publication has 14 references indexed in Scilit:
- A Lightweight Sparse Focus Transformer for Remote Sensing Image Change CaptioningIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024
- Single-Stream Extractor Network With Contrastive Pre-Training for Remote-Sensing Change CaptioningIEEE Transactions on Geoscience and Remote Sensing, 2024
- Change Captioning for Satellite Images Time SeriesIEEE Geoscience and Remote Sensing Letters, 2024
- A Decoupling Paradigm With Prompt Learning for Remote Sensing Image Change CaptioningIEEE Transactions on Geoscience and Remote Sensing, 2023
- Implicit Diffusion Models for Continuous Super-Resolution2023
- Remote Sensing Image Change Captioning With Dual-Branch Transformers: A New Method and a Large Scale DatasetIEEE Transactions on Geoscience and Remote Sensing, 2022
- Change Captioning: A New Paradigm for Multitemporal Remote Sensing Image AnalysisIEEE Transactions on Geoscience and Remote Sensing, 2022
- Captioning Changes in Bi-Temporal Remote Sensing Images2021
- Robust Change Captioning2019
- CIDEr: Consensus-based image description evaluation2015