用状态空间模型专注检测遥感图像变化，更高效且准确。
Efficient Remote Sensing Change Detection with Change State Space Models
- 聚焦双时相图像变化区域，只处理相关特征。
- 参数量少，计算复杂度仅为同类模型的1/4，性能更优。
- 适合大规模遥感变化检测任务，尤其对算力有限场景友好。
尽管卷积网络和视觉变压器（ViT）常用于变化检测，但前者难以建模长距离依赖，后者计算效率低，难以在大规模数据集上训练。基于状态空间模型的视觉马尔可夫（Vision Mamba）虽作为替代方案出现，但多仅用作特征提取主干。本文提出专为变化检测设计的改变状态空间模型（CSSM），通过聚焦双时相图像间的相关变化，有效过滤无关信息。仅关注变化特征使参数量显著减少，大幅提高计算效率，同时保持高检测性能和对输入退化的鲁棒性。在三个基准数据集上的评估显示，其性能超越卷积网络、视觉变压器及基于马尔可夫的模型，且计算复杂度仅为后者的几分之一。代码将在论文接受后开源。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。