HCGMNET: A Hierarchical Change Guiding Map Network For Change Detection

TL;DR

HCGMNet is a hierarchical deep learning model designed for high-resolution remote sensing image change detection, effectively capturing multiscale features and refining edge details through a change guide module, outperforming existing methods.

Contribution

The paper introduces HCGMNet, a novel hierarchical network with a change guide module that enhances change detection accuracy in VHR remote sensing images.

Findings

HCGMNet outperforms state-of-the-art methods on two datasets.

Hierarchical feature extraction improves global and local information representation.

The change guide module effectively refines edge features.

Abstract

Very-high-resolution (VHR) remote sensing (RS) image change detection (CD) has been a challenging task for its very rich spatial information and sample imbalance problem. In this paper, we have proposed a hierarchical change guiding map network (HCGMNet) for change detection. The model uses hierarchical convolution operations to extract multiscale features, continuously merges multi-scale features layer by layer to improve the expression of global and local information, and guides the model to gradually refine edge features and comprehensive performance by a change guide module (CGM), which is a self-attention with changing guide map. Extensive experiments on two CD datasets show that the proposed HCGMNet architecture achieves better CD performance than existing state-of-the-art (SOTA) CD methods.