Remote Sensing Image Change Detection with Graph Interaction

TL;DR

This paper introduces BGINet-CD, a novel graph interaction network for remote sensing change detection that improves feature interaction between bitemporal images, leading to better accuracy and efficiency.

Contribution

The paper proposes a unified self-focus mechanism using graph interactions and non-local operations to enhance feature coupling in change detection.

Findings

Outperforms state-of-the-art methods on GZ CD dataset

Achieves a better balance between accuracy and computational efficiency

Demonstrates robustness with a streamlined ResNet18 backbone

Abstract

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