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.

翻译：尽管卷积神经网络（ConvNets）和视觉变换器（ViT）在变化检测中应用频繁，但二者均存在明显局限：前者难以建模长程依赖关系，而后者计算效率低下，使其难以在大规模数据集上训练。基于状态空间模型的视觉Mamba架构作为一种替代方案出现，解决了上述不足，并已应用于遥感变化检测，但主要作为特征提取骨干网络。本文提出了专门为变化检测设计的Change State Space Model，该模型通过聚焦双时相图像间的相关变化，有效过滤无关信息。通过仅关注变化特征，网络参数量得以减少，在保持高检测性能和输入退化鲁棒性的同时，显著提升了计算效率。所提模型在三个基准数据集上进行了评估，结果表明其以远低于ConvNets、ViTs及基于Mamba的对比模型的计算复杂度，实现了更优性能。代码将在论文录用后发布于https://github.com/Elman295/CSSM。