Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection

TL;DR

This paper introduces a novel change detection method in remote sensing that combines precision spatio-temporal feature fusion, efficient global context modeling, and an optimized loss function, resulting in improved accuracy and robustness.

Contribution

It proposes a new fusion approach with precision blocks, an enhanced decoder, and a combined loss function, advancing the state-of-the-art in remote sensing change detection.

Findings

Outperforms existing methods on SYSU-CD, LEVIR-CD+, and WHU-CD datasets.

Achieves higher precision, recall, F1 score, IoU, and accuracy.

Demonstrates robustness and efficiency in complex scenes.

Abstract

Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as convolutional neural networks (CNNs), struggle to capture long-range dependencies and global context essential for accurate change detection in complex scenes. While Transformer-based models mitigate these issues, their computational complexity limits their applicability in high-resolution remote sensing. Building upon ChangeMamba architecture, which leverages state space models for efficient global context modeling, this paper proposes precision fusion blocks to capture channel-wise temporal variations and per-pixel differences for fine-grained change detection. An enhanced decoder pipeline, incorporating lightweight channel reduction mechanisms, preserves local details with minimal computational cost. Additionally, an optimized loss function combining Cross Entropy, Dice and Lovasz objectives addresses class imbalance and boosts Intersection-over-Union (IoU). Evaluations on SYSU-CD, LEVIR-CD+, and WHU-CD datasets demonstrate superior precision, recall, F1 score, IoU, and overall accuracy compared to state-of-the-art methods, highlighting the approach's robustness for remote sensing change detection. For complete transparency, the codes and pretrained models are accessible at https://github.com/Buddhi19/MambaCD.git