Remote Sensing Image Change Captioning Using Multi-Attentive Network with Diffusion Model

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2024-11, Vol.16 (21), p.4083
• Main Authors: Yang, Yue, Liu, Tie, Pu, Ying, Liu, Liangchen, Zhao, Qijun, Wan, Qun
• Format: Article
• Language: English
• Subjects: Analysis; Attention; attention mechanism; change captioning (CC); Computational linguistics; Datasets; Diffusion; diffusion model; Feature extraction; image captioning; Image degradation; Information processing; Language; Language processing; Large language models; Natural language; Natural language interfaces; Neural networks; Object recognition; Remote sensing; remote sensing (RS); Representations; Semantics
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs16214083

Remote sensing image change captioning (RSICC) has received considerable research interest due to its ability of automatically providing meaningful sentences describing the changes in remote sensing (RS) images. Existing RSICC methods mainly utilize pre-trained networks on natural image datasets to extract feature representations. This degrades performance since aerial images possess distinctive characteristics compared to natural images. In addition, it is challenging to capture the data distribution and perceive contextual information between samples, resulting in limited robustness and generalization of the feature representations. Furthermore, their focus on inherent most change-aware discriminative information is insufficient by directly aggregating all features. To deal with these problems, a novel framework entitled Multi-Attentive network with Diffusion model for RSICC (MADiffCC) is proposed in this work. Specifically, we introduce a diffusion feature extractor based on RS image dataset pre-trained diffusion model to capture the multi-level and multi-time-step feature representations of bitemporal RS images. The diffusion model is able to learn the training data distribution and contextual information of RS objects from which more robust and generalized representations could be extracted for the downstream application of change captioning. Furthermore, a time-channel-spatial attention (TCSA) mechanism based difference encoder is designed to utilize the extracted diffusion features to obtain the discriminative information. A gated multi-head cross-attention (GMCA)-guided change captioning decoder is then proposed to select and fuse crucial hierarchical features for more precise change description generation. Experimental results on the publicly available LEVIR-CC, LEVIRCCD, and DUBAI-CC datasets verify that the developed approach could realize state-of-the-art (SOTA) performance.