Remote Sensing Image Change Detection with Graph Interaction
This work addresses change detection in remote sensing images, offering improved accuracy and computational efficiency, but it is incremental as it builds on existing backbone architectures and non-local operations.
The paper tackles the problem of remote sensing image change detection by proposing BGINet-CD, a graph interaction network that enhances information coupling between bitemporal images and suppresses irrelevant interference, achieving superior performance on the GZ CD dataset compared to state-of-the-art methods.
Modern remote sensing image change detection has witnessed substantial advancements by harnessing the potent feature extraction capabilities of CNNs and Transforms.Yet,prevailing change detection techniques consistently prioritize extracting semantic features related to significant alterations,overlooking the viability of directly interacting with bitemporal image features.In this letter,we propose a bitemporal image graph Interaction network for remote sensing change detection,namely BGINet-CD. More specifically,by leveraging the concept of non-local operations and mapping the features obtained from the backbone network to the graph structure space,we propose a unified self-focus mechanism for bitemporal images.This approach enhances the information coupling between the two temporal images while effectively suppressing task-irrelevant interference,Based on a streamlined backbone architecture,namely ResNet18,our model demonstrates superior performance compared to other state-of-the-art methods (SOTA) on the GZ CD dataset. Moreover,the model exhibits an enhanced trade-off between accuracy and computational efficiency,further improving its overall effectiveness