Consistency Change Detection Framework for Unsupervised Remote Sensing Change Detection

TL;DR

This paper introduces a novel unsupervised change detection framework for remote sensing images that reduces generator overfitting and improves change detection accuracy through cycle and semantic consistency modules.

Contribution

The paper proposes a new Consistency Change Detection Framework with cycle and semantic modules to enhance unsupervised remote sensing change detection.

Findings

Outperforms state-of-the-art methods in experiments

Reduces generator overfitting with cycle consistency

Enhances detail reconstruction with semantic consistency

Abstract

Unsupervised remote sensing change detection aims to monitor and analyze changes from multi-temporal remote sensing images in the same geometric region at different times, without the need for labeled training data. Previous unsupervised methods attempt to achieve style transfer across multi-temporal remote sensing images through reconstruction by a generator network, and then capture the unreconstructable areas as the changed regions. However, it often leads to poor performance due to generator overfitting. In this paper, we propose a novel Consistency Change Detection Framework (CCDF) to address this challenge. Specifically, we introduce a Cycle Consistency (CC) module to reduce the overfitting issues in the generator-based reconstruction. Additionally, we propose a Semantic Consistency (SC) module to enable detail reconstruction. Extensive experiments demonstrate that our method outperforms other state-of-the-art approaches.