Mask Approximation Net: A Novel Diffusion Model Approach for Remote Sensing Change Captioning
- 10 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-11
Abstract
Remote sensing image change description represents an innovative multimodal task within the realm of remote sensing processing. This task not only facilitates the detection of alterations in surface conditions, but also provides comprehensive descriptions of these changes, thereby improving human interpretability and interactivity. Current deep learning methods typically adopt a three-stage framework consisting of feature extraction, feature fusion, and change localization, followed by text generation. Most approaches focus heavily on designing complex network modules but lack solid theoretical guidance, relying instead on extensive empirical experimentation and iterative tuning of network components. This experience-driven design paradigm may lead to overfitting and design bottlenecks, thereby limiting the model’s generalizability and adaptability. To address these limitations, this paper proposes a paradigm that shift towards data distribution learning using diffusion models, reinforced by frequency-domain noise filtering, to provide a theoretically motivated and practically effective solution to multimodal remote sensing change description. The proposed method primarily includes a simple multi-scale change detection module, whose output features are subsequently refined by a well-designed diffusion model. Furthermore, we introduce a frequency-guided complex filter module to boost the model performance by managing high-frequency noise throughout the diffusion process. We validate the effectiveness of our proposed method across several datasets for remote sensing change detection and description, showcasing its superior performance compared to existing techniques. The code will be available at MaskApproxNet.Keywords
All Related Versions
Funding Information
- Key Research and Development Program of Zhejiang (2025C01075)
- National Natural Science Foundation of China (62272375)
- National Natural Science Foundation of China (62201553)
- National Natural Science Foundation of China (12201145)
- Project of Chinese Academy of Engineering “The Online and Offline Mixed Educational Service System for “The Belt and Road” Training in MOOC China”;
- Natural Science Foundation of Guangdong Province (2022A1515110336)
- Yongjiang Science and Technology Innovation 2035 Key Research and Development Program (2025Z191)
This publication has 42 references indexed in Scilit:
- GeoChat:Grounded Large Vision-Language Model for Remote Sensing2024
- CD-GAN: A robust fusion-based generative adversarial network for unsupervised remote sensing change detection with heterogeneous sensorsInformation Fusion, 2024
- Semantic-Conditional Diffusion Networks for Image Captioning*2023
- Implicit Diffusion Models for Continuous Super-Resolution2023
- Describing and Localizing Multiple Changes with Transformers2021
- Image Change Captioning by Learning from an Auxiliary Task2021
- Robust Change Captioning2019
- Fully Convolutional Siamese Networks for Change Detection2018
- CIDEr: Consensus-based image description evaluation2015
- Automatic analysis of the difference image for unsupervised change detectionIEEE Transactions on Geoscience and Remote Sensing, 2000