FDANet: Lightweight Attention with Feature Differences for Efficient Change Detection

This letter presents a low-complexity attention module for fast change detection.

The proposed module computes the absolute difference between bi-temporal features extracted by a Siamese backbone network and sequentially applies spatial and channel attention to generate key change representations. Spatial attention emphasizes important spatial locations using representative values from channel-wise pooling, while channel attention highlights discriminative feature responses using values from spatial-wise pooling. By leveraging low-dimensional representative features, the module significantly reduces computational cost. Additionally, its dual-attention structure—driven by feature differences—enhances both spatial localization and semantic relevance of changes.

Compared to the Change-Guided Network (CGNet), the proposed method reduces multiply-accumulate operations (MACs) by 53.81% with only a 0.15% drop in F1-score, demonstrating high efficiency with minimal performance degradation. These results suggest that the proposed method is suitable for large-scale or real-time remote sensing applications where computational efficiency is essential.