遥感变化检测中的状态空间模型变换

Change State Space Models for Remote Sensing Change Detection

April 15, 2025

作者: Elman Ghazaei, Erchan Aptoula

cs.AI

摘要

尽管卷积神经网络（ConvNets）和视觉Transformer（ViT）在变化检测中频繁使用，但两者均存在众所周知的局限性：前者难以建模长程依赖关系，而后者计算效率低下，这使得它们在大规模数据集上的训练颇具挑战。基于状态空间模型的Vision Mamba架构应运而生，旨在解决上述不足，并已应用于遥感变化检测，尽管主要作为特征提取的主干网络。本文提出的变化状态空间模型（Change State Space Model, CSSM），专为变化检测设计，通过聚焦于双时相图像间的相关变化，有效滤除无关信息。该模型仅关注变化特征，从而减少了网络参数数量，显著提升了计算效率，同时保持了高检测性能和对输入退化的鲁棒性。通过在三个基准数据集上的评估，所提模型以远低于ConvNets、ViTs及Mamba类模型的计算复杂度，实现了性能上的超越。模型实现将在论文录用后发布于https://github.com/Elman295/CSSM。

English

Despite their frequent use for change detection, both ConvNets and Vision transformers (ViT) exhibit well-known limitations, namely the former struggle to model long-range dependencies while the latter are computationally inefficient, rendering them challenging to train on large-scale datasets. Vision Mamba, an architecture based on State Space Models has emerged as an alternative addressing the aforementioned deficiencies and has been already applied to remote sensing change detection, though mostly as a feature extracting backbone. In this article the Change State Space Model is introduced, that has been specifically designed for change detection by focusing on the relevant changes between bi-temporal images, effectively filtering out irrelevant information. By concentrating solely on the changed features, the number of network parameters is reduced, enhancing significantly computational efficiency while maintaining high detection performance and robustness against input degradation. The proposed model has been evaluated via three benchmark datasets, where it outperformed ConvNets, ViTs, and Mamba-based counterparts at a fraction of their computational complexity. The implementation will be made available at https://github.com/Elman295/CSSM upon acceptance.