Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices
IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-11
DOI: 10.1109/tgrs.2025.3585342 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Blaž Rolih und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: Slovenian Research and Innovation Agency (ARIS) Research Project, Research Programme P2-0214, Supercomputing Network SLING.
Abstract (Originalsprache)
Remote sensing change detection aims to localize semantic changes between images of the same location captured at different times. In the past few years, newer methods have attributed enhanced performance to the additions of new and complex components to existing architectures. Most fail to measure the performance contribution of fundamental design choices, such as backbone selection, pretraining strategies, and training configurations. We claim that such fundamental design choices often improve performance even more significantly than the addition of new architectural components. Due to that, we systematically revisit the design space of change detection models and analyse the full potential of a well-optimized baseline. We identify a set of fundamental design choices that benefit both new and existing architectures. Leveraging this insight, we demonstrate that when carefully designed, even an architecturally simple model can match or surpass state-of-the-art performance on six challenging change detection datasets. Our best practices generalize beyond our architecture and also offer performance improvements when applied to related methods, indicating that the space of fundamental design choices has been underexplored. Our guidelines and architecture provide a strong foundation for future methods, emphasizing that optimizing core components is just as important as architectural novelty in advancing change detection performance. Code is at: https://github.com/blaz-r/BTC-change-detection
Förderung
- Slovenian Research and Innovation Agency (ARIS) Research Project
- Research Programme P2-0214
- Supercomputing Network SLING
Zitieren
APA
Rolih, B., Fučka, M., Wolf, F., & Zajc, L. Č. (2025). Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-11. https://doi.org/10.1109/tgrs.2025.3585342
Vancouver
Rolih B, Fučka M, Wolf F, Zajc LČ. Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-11. doi:10.1109/tgrs.2025.3585342
BibTeX
@article{Rolih2025,
author = {Rolih, Blaž and Fučka, Matic and Wolf, Filip and Zajc, Luka Čehovin},
title = {Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2025},
volume = {63},
pages = {1--11},
doi = {10.1109/tgrs.2025.3585342}
}
EUVIMED