ESIFCD: A Dual-Temporal Cross-Domain Fusion Network for Remote Sensing Change Detection
Open Access
- 23 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 167227-167249
Abstract
Remote sensing change detection (RSCD) must remain reliable under illumination, seasonal, and viewpoint variability while handling objects that range from narrow roads to block-scale complexes. We present Efficient Spectral Inception Former Change Detector (ESIFCD), an efficient dual-temporal network that couples domain-aligned differencing with multiple cross-resolution exchange and lightweight global context encoding. ESIFCD introduces: (i) an Adaptive Difference Fusion Unit (ADFU) that fuses absolute and learned differences over spatial, spectral, and texture features; (ii) a Cross-Resolution Aggregation Module (CRAM) that repeatedly exchanges evidence among four scales to mitigate scale disagreement; (iii) a Patch-Aware Context Encoder (PACE) that models long-range dependencies via tokenized patches with modest cost; and (iv) a fast GLCM-Stats Encoder that supplies texture semantics (ASM/Contrast/Correlation) without analytical histograms. A re-parameterized large-kernel block (RLKB) sharpens local detail, and a late MetaCNNGate learns pixel-wise weights over one primary and four auxiliary heads to consolidate their complementary expertise (small vs. large structures). Across six public benchmarks, ESIFCD attains the best F1 on each dataset: 93.19% (LEVIR-CD), 87.89% (LEVIR-CD+), 70.10% (S2Looking), 95.95% (CDD), 83.48% (SYSU-CD), and 95.30% (WHU-CD). The model is efficient and fast (12.33 GFLOPs; 82.07 images/s at 2562), and with automatic mixed precision reaches over 165 images/s while maintaining accuracy, surpassing recent strong baselines under the same setting. Ablations confirm that ADFU improves robustness to radiometric and registration noise, CRAM preserves thin structures and prevents fragmentation on large objects, PACE improves cluttered scenes, and MetaCNNGate consistently lifts F1 on all benchmarks.Keywords
Funding Information
- 2025 Research Fund of University of Ulsan
This publication has 43 references indexed in Scilit:
- Frequency and Texture Aware Multi-Domain Feature Fusion for Remote Sensing Scene ClassificationIEEE Access, 2024
- Deep learning change detection techniques for optical remote sensing imagery: Status, perspectives and challengesInternational Journal of Applied Earth Observation and Geoinformation, 2024
- Single-Temporal Supervised Learning for Universal Remote Sensing Change DetectionInternational Journal of Computer Vision, 2024
- U2-Net: Going deeper with nested U-structure for salient object detectionPattern Recognition, 2020
- A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing imagesISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Feature Pyramid Networks for Object Detection2017
- ImageNet: A large-scale hierarchical image database2009
- Multivariate Alteration Detection (MAD) and MAF Postprocessing in Multispectral, Bitemporal Image Data: New Approaches to Change Detection StudiesRemote Sensing of Environment, 1998
- Review Article Digital change detection techniques using remotely-sensed dataInternational Journal of Remote Sensing, 1989