EUVIMEDEUVIMED entdecken
Crossref

Continual Test-Time Adaptive Object Detection in Remote Sensing Images via Spectral Routing and Historical Reconstruction

Mingjing Yong, Nanqing Liu, Sen Lei, Jie Pan, Xue Yang, Heng-Chao Li

IEEE Transactions on Circuits and Systems for Video Technology · 2026-09 · 36 (9) · 12875-12888

DOI: 10.1109/tcsvt.2026.3689532 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-09. Verfasst von Mingjing Yong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province, Fellowship of China National Postdoctoral Program for Innovative Talents.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing object detection (RSOD) remains challenging due to significant domain shifts caused by variations in sensors, geographic regions, illumination, weather, and object scales, which severely degrade model performance when deployed on unseen target domains. While test-time adaptation (TTA) enables model updating using unlabeled test data, existing methods typically assume relatively stable target distributions and struggle under the dynamic and sequential conditions of remote sensing scenarios. Continual test-time adaptation for object detection (CTAOD) further extends TTA to streaming test data, but current approaches often rely on global updates with fixed criteria, resulting in noisy feature propagation, error accumulation, and catastrophic forgetting. In this paper, we propose CTAOD-RS, a novel framework for continual test-time adaptive object detection in remote sensing imagery. The proposed framework leverages Spectral Routing Adaptation to decompose features into frequency and spatial components, suppressing noise and clutter, and employs History-Informed Reconstruction to dynamically determine when model adaptation is necessary, avoiding unnecessary updates and mitigating catastrophic forgetting. Extensive experiments on benchmark RSOD datasets, including the newly introduced DIOR-C corrupted benchmark designed to simulate realistic remote sensing domain shifts, demonstrate superior detection accuracy and robustness compared to existing TTA and CTAOD methods, while maintaining high efficiency. The code will be released at https://github.com/rosou1/CTAOD-RS

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Sichuan Province
  • Fellowship of China National Postdoctoral Program for Innovative Talents

Zitieren

APA

Yong, M., Liu, N., Lei, S., Pan, J., Yang, X., & Li, H. (2026). Continual Test-Time Adaptive Object Detection in Remote Sensing Images via Spectral Routing and Historical Reconstruction. IEEE Transactions on Circuits and Systems for Video Technology, 36(9), 12875-12888. https://doi.org/10.1109/tcsvt.2026.3689532

Vancouver

Yong M, Liu N, Lei S, Pan J, Yang X, Li H. Continual Test-Time Adaptive Object Detection in Remote Sensing Images via Spectral Routing and Historical Reconstruction. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(9):12875-12888. doi:10.1109/tcsvt.2026.3689532

BibTeX
@article{Yong2026,
  author = {Yong, Mingjing and Liu, Nanqing and Lei, Sen and Pan, Jie and Yang, Xue and Li, Heng-Chao},
  title = {Continual Test-Time Adaptive Object Detection in Remote Sensing Images via Spectral Routing and Historical Reconstruction},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {9},
  pages = {12875--12888},
  doi = {10.1109/tcsvt.2026.3689532}
}
Kostenlos starten →