A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection

Short summary

A novel Siamese-based spatial–temporal attention neural network, incorporating a self-attention module that models relationships between pixels across different times and locations, improved the F1-score of a baseline model from 83.9 to 87.3 on remote sensing image change detection.

AI-generated from the title and abstract; the full text is not read.