A Mamba-based Siamese Network for Remote Sensing Change Detection

TL;DR

This paper introduces a Mamba-based Siamese network for remote sensing change detection, offering faster training and better segmentation than transformer-based models, with significant improvements demonstrated on multiple datasets.

Contribution

The paper presents a novel Mamba-based architecture for change detection that outperforms existing methods in accuracy and efficiency.

Findings

Significant accuracy improvements over SOTA methods.

Linear-time training capability of the Mamba architecture.

Enhanced receptive field compared to transformers.

Abstract

Change detection in remote sensing images is an essential tool for analyzing a region at different times. It finds varied applications in monitoring environmental changes, man-made changes as well as corresponding decision-making and prediction of future trends. Deep learning methods like Convolutional Neural Networks (CNNs) and Transformers have achieved remarkable success in detecting significant changes, given two images at different times. In this paper, we propose a Mamba-based Change Detector (M-CD) that segments out the regions of interest even better. Mamba-based architectures demonstrate linear-time training capabilities and an improved receptive field over transformers. Our experiments on four widely used change detection datasets demonstrate significant improvements over existing state-of-the-art (SOTA) methods. Our code and pre-trained models are available at https://github.com/JayParanjape/M-CD