Real-CD: Change Detection Under Real-World Complex Interference via Dynamic Distribution Correction
IEEE Transactions on Image Processing · 2026 · 35 · 4295-4309
DOI: 10.1109/tip.2026.3684407 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Leyuan Fang und 3 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China.
Abstract (Originalsprache)
While change detection (CD) is crucial for tracking dynamic changes on the Earth's surface, it faces substantial challenges in real-world settings caused by seasonal variations and sensor-related interference. Current CD models often suffer performance degradation under such conditions, mainly due to two key challenges. First, most existing CD datasets lack sufficient temporal and environmental diversity, as they are typically collected over constrained time spans. This limits the models' ability to generalize across varying conditions. Second, many CD methods are heavily data-driven and rely on simplified assumptions, leading to models that are not adequately designed to handle the complex, heterogeneous nature of real-world scenarios. Together, these challenges restrict the robustness and practical applicability of current CD approaches. To overcome these challenges, we make the following contributions in this paper: 1) Regarding data diversity, we construct a comprehensive benchmark by introducing five typical perturbations (fog, snow, motion blur, Gaussian noise, and impulse noise) into three classical CD datasets and supplementing them with a real-world seasonal dataset, resulting in 75 interference-rich scenarios. This enables a systematic evaluation under diverse real-world conditions, revealing that such perturbations induce severe distribution shifts across both temporal phases and hierarchical network layers, leading to substantial performance degradation in existing models. 2) Algorithmically, we propose Real-CD, a novel method specifically designed to address distribution shifts in real-world CD. The core of Real-CD is to leverage bi-temporal correlations to perform adaptive distribution alignment across hierarchical layers and temporal phases. Specifically, we propose the Distribution Shifts Alleviation Module (DSAM) to correct distribution shifts. The DSAM captures bi-temporal differences and similarities to formulate temporal-specific adjustment strategies for each LayerNorm (LN) layer. To stabilize the optimization of DSAM, we propose the Distribution Consistency Optimization Strategy (DCOS), which introduces a flip-based auxiliary task that encourages the model to maintain distributional consistency under complex bi-temporal disturbances. Consequently, our method outperforms other state-of-the-art approaches and achieves the best performance on the proposed dataset. Our datasets and code implementation will be available at https://github.com/fangyee-ISALAB/Real-CD.
Förderung
- National Natural Science Foundation of China
- Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
Zitieren
APA
Fang, L., Fang, Y., Ghamisi, P., & Liu, Q. (2026). Real-CD: Change Detection Under Real-World Complex Interference via Dynamic Distribution Correction. IEEE Transactions on Image Processing, 35, 4295-4309. https://doi.org/10.1109/tip.2026.3684407
Vancouver
Fang L, Fang Y, Ghamisi P, Liu Q. Real-CD: Change Detection Under Real-World Complex Interference via Dynamic Distribution Correction. IEEE Transactions on Image Processing. 2026;35:4295-4309. doi:10.1109/tip.2026.3684407
BibTeX
@article{Fang2026,
author = {Fang, Leyuan and Fang, Yi and Ghamisi, Pedram and Liu, Qiang},
title = {Real-CD: Change Detection Under Real-World Complex Interference via Dynamic Distribution Correction},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {4295--4309},
doi = {10.1109/tip.2026.3684407}
}
EUVIMED