Existing methods in remote sensing image scene change detection typically rely on convolutional or Transformer architectures to extract attribute features, combining local details with global semantic modeling. However, these approaches often overlook the importance of neighborhood attribute features for capturing local changes and contextual stability, leading to insuf-ficient representation of fine-grained changes. Additionally, bi-temporal feature fusion commonly suffers from information loss, limiting the depth of interaction modeling in change regions and impacting both accuracy and robustness. To address these chal-lenges, we propose a novel dual-temporal remote sensing scene change understanding network with multi-scale neighbor-hood decoupling and attribute-focused fusion (MNDAF-Net). In the encoding phase, we leverage a multi-scale neighborhood feature decoupling analysis module to enhance independent modeling of neighborhood attributes, effectively capturing fine-grained changes in complex scenes. Specifically, this module integrates multi-head adjacent atrous attention (MA²) and a panoramic adaptive attribute sensing layer (PA²S) to provide comprehensive multi-scale perception and adaptive feature enhancement for bi-temporal remote sensing images. In the decoding phase, the at-tribute-focused fusion decoder (AFF-Decoder) enhances the fusion of bi-temporal features by ensuring correlated interactions between dual-temporal features, capturing fine-grained relation-ships to achieve more accurate change representations. Experi-mental results on three public datasets—LEVIR-CD, WHU-CD, and DSIFN-CD—demonstrate that the proposed MNDAF-Net achieves promising performance in remote sensing attribute change understanding. Our code will be published at https://github.com/lzp-lkd/MNDAF-Net.
No takes yet. Share an insight, caveat, or question.
Li et al. (2025) studied this question.