Relating CNN-Transformer Fusion Network for Change Detection
This work addresses limitations in remote sensing change detection for applications like environmental monitoring, though it appears incremental as it builds on existing CNN and transformer methods.
The paper tackled the problem of missing crucial features in remote sensing change detection by proposing RCTNet, a CNN-Transformer fusion network that integrates early fusion, cross-stage aggregation, multi-scale feature fusion, and efficient self-deciphering attention, resulting in significant improvement and an optimal balance between accuracy and computational cost.
While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change learning. Additionally, transformer networks struggle with low-level details. RCTNet addresses these limitations by introducing \textbf{(1)} an early fusion backbone to exploit both spatial and temporal features early on, \textbf{(2)} a Cross-Stage Aggregation (CSA) module for enhanced temporal representation, \textbf{(3)} a Multi-Scale Feature Fusion (MSF) module for enriched feature extraction in the decoder, and \textbf{(4)} an Efficient Self-deciphering Attention (ESA) module utilizing transformers to capture global information and fine-grained details for accurate change detection. Extensive experiments demonstrate RCTNet's clear superiority over traditional RS image CD methods, showing significant improvement and an optimal balance between accuracy and computational cost.