DDLNet: Boosting Remote Sensing Change Detection with Dual-Domain Learning

TL;DR

DDLNet introduces dual-domain learning for remote sensing change detection, combining frequency and spatial domain features to improve accuracy and efficiency in identifying changes across multi-temporal images.

Contribution

The paper proposes DDLNet, a novel RSCD network that integrates frequency-domain enhancement with spatial-domain feature recovery for improved change detection.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Provides a better accuracy-efficiency trade-off.

Demonstrates effectiveness of dual-domain learning in RSCD.

Abstract

Remote sensing change detection (RSCD) aims to identify the changes of interest in a region by analyzing multi-temporal remote sensing images, and has an outstanding value for local development monitoring. Existing RSCD methods are devoted to contextual modeling in the spatial domain to enhance the changes of interest. Despite the satisfactory performance achieved, the lack of knowledge in the frequency domain limits the further improvement of model performance. In this paper, we propose DDLNet, a RSCD network based on dual-domain learning (i.e., frequency and spatial domains). In particular, we design a Frequency-domain Enhancement Module (FEM) to capture frequency components from the input bi-temporal images using Discrete Cosine Transform (DCT) and thus enhance the changes of interest. Besides, we devise a Spatial-domain Recovery Module (SRM) to fuse spatiotemporal features for reconstructing spatial details of change representations. Extensive experiments on three benchmark RSCD datasets demonstrate that the proposed method achieves state-of-the-art performance and reaches a more satisfactory accuracy-efficiency trade-off. Our code is publicly available at https://github.com/xwmaxwma/rschange.