FASI-Net: Frequency-Domain Information Assisted Semantic Interaction Network for Bitemporal Remote Sensing Images Change Detection

As a crucial approach for comprehending land surface changes, remote sensing images (RSIs) change detection methods based on deep learning have been extensively studied in recent years. Among these methods, the Siamese network-based method has demonstrated remarkable performance. However, existing approaches are susceptible to interference from irrelevant factors such as shadows, noise, and unrelated changes in a single temporal, which limits the model's ability to accurately perceive bitemporal crucial semantic information. To address the abovementioned problems, this article proposes a frequency-domain information assisted semantic interaction network (FASI-Net) to ensure the effective extraction of crucial semantic information in the original bitemporal features. We attempt to employ frequency-domain information to explicitly interact bitemporal low-frequency semantic information during the encoding process, subsequently preserving and enhancing the high-frequency information of each temporal feature. This enables model comprehensive perception of bitemporal features, effectively distinguishing the semantic similar information from the semantic difference information, and accurately identifying changed regions versus unchanged regions. Extensive experiments on three typical RSIs change detection datasets demonstrate a significant improvement in the performance of our proposed method (with 4.53%/7.57%, 6.66%/10.69%, and 5.11%/7.24% improvements over the baseline in terms of F1/intersection over union (IoU) metrics for WHU-CD, LEVIR-CD, and SYSU-CD datasets). Moreover, our FASI-Net comprehensively achieves state-of-the-art results with F1/IoU reaching 92.86%/86.67%, 91.73%/84.71%, and 83.72%/72.00% on WHU-CD, LEVIR-CD, and SYSU-CD datasets, respectively. In addition, the proposed bitemporal low-frequency semantic interaction module can be seamlessly inserted into existing change detection models to achieve effective crucial semantic information extraction.