A Remote Sensing Image Change Detection Method Integrating Layer Exchange and Channel-Spatial Differences

TL;DR

This paper introduces LENet, a change detection model for remote sensing images that integrates a Channel-Spatial Difference Weighting module and a Layer-Exchange decoding structure to improve sensitivity and inter-image feature interaction.

Contribution

The study proposes novel modules for change detection that leverage both spatial and channel differences and a layer-exchange decoding structure to enhance bi-temporal feature interaction.

Findings

Significant improvement in change detection accuracy on multiple datasets.

The proposed modules effectively enhance sensitivity to difference features.

LENet outperforms existing methods in benchmark evaluations.

Abstract

Change detection in remote sensing imagery is a critical technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bi-temporal images. The essence of pixel-level change detection lies in determining whether corresponding pixels in bi-temporal images have changed. In deep learning, the spatial and channel dimensions of feature maps represent different information from the original images. In this study, we found that in change detection tasks, difference information can be computed not only from the spatial dimension of bi-temporal features but also from the channel dimension. Therefore, we designed the Channel-Spatial Difference Weighting (CSDW) module as an aggregation-distribution mechanism for bi-temporal features in change detection. This module enhances the sensitivity of the change detection model to difference features. Additionally, bi-temporal images share the same geographic location and exhibit strong inter-image correlations. To construct the correlation between bi-temporal images, we designed a decoding structure based on the Layer-Exchange (LE) method to enhance the interaction of bi-temporal features. Comprehensive experiments on the CLCD, PX-CLCD, LEVIR-CD, and S2Looking datasets demonstrate that the proposed LENet model significantly improves change detection performance. The code and pre-trained models will be available at: https://github.com/dyzy41/lenet.