CDxLSTM: Boosting Remote Sensing Change Detection With Extended Long Short-Term Memory

Abstract

In complex scenes and varied conditions, effectively integrating spatial-temporal context is crucial for accurately identifying changes. However, current remote sensing change detection (RS-CD) methods lack a balanced consideration of performance and efficiency. CNNs lack global context, transformers are computationally expensive, and Mambas face compute unified device architecture (CUDA) dependence and local correlation loss. In this letter, we propose CDxLSTM, with a core component that is a powerful xLSTM-based feature enhancer (FE) layer, integrating the advantages of linear computational complexity, global context perception, and strong interpretability. Specifically, we introduce a scale-specific FE layer, incorporating a cross-temporal global perceptron (CTGP) customized for semantic-accurate deep features, and a cross-temporal spatial refiner (CTSR) customized for detail-rich shallow features. In addition, we propose a cross-scale interactive fusion (CSIF) module to progressively interact global change representations with spatial responses. Extensive experimental results demonstrate that CDxLSTM achieves state-of-the-art performance across three benchmark datasets, offering a compelling balance between efficiency and accuracy. Code is available at https://github.com/xwmaxwma/rschange