EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DyPerceiver-Det: Instance-Wise Dynamic Perception for Fine-Grained Oriented Object Detection in Remote Sensing Images

Tao Liu, Qianqian Liu, Xiaoyu Zuo

Remote Sensing · 02.08.2026 · 18 (15) · 2515

DOI: 10.3390/rs18152515 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.08.2026. Verfasst von Tao Liu und 2 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fine-grained oriented object detection in remote sensing is challenged by extreme scale variation, arbitrary rotations, and dense layouts with structured clutter, where fixed feature selection and RoI extraction often lead to unstable localization and intra-class confusion. We propose DyPerceiver-Det, a plug-and-play Dynamic Perception RoI Extractor for RoI-based oriented detectors. Given multi-level feature maps and oriented proposals, DyPerceiver-Det refines each RoI representation along three complementary dimensions: Dynamic Scale Perception (DSP) for instance-wise multi-level feature fusion, Dynamic Channel Perception (DCP) for RoI-specific channel gating to suppress background-dominant responses, and Dynamic Orientation Perception (DOP) for orientation-aligned local sampling with learnable refinement. We further introduce sparsity and consistency regularization to make dynamic decisions selective and stable under strong geometric augmentations. Extensive experiments on FAIR1M and MAR20 under a unified evaluation protocol demonstrate consistent improvements over strong oriented baselines, with more pronounced gains on small objects and crowded regions. Qualitative visualizations and fine-grained confusion analyses provide interpretable evidence that dynamic perception reduces feature misalignment and sibling-class confusions with modest computational overhead.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, T., Liu, Q., & Zuo, X. (2026). DyPerceiver-Det: Instance-Wise Dynamic Perception for Fine-Grained Oriented Object Detection in Remote Sensing Images. Remote Sensing, 18(15), 2515. https://doi.org/10.3390/rs18152515

Vancouver

Liu T, Liu Q, Zuo X. DyPerceiver-Det: Instance-Wise Dynamic Perception for Fine-Grained Oriented Object Detection in Remote Sensing Images. Remote Sensing. 2026;18(15):2515. doi:10.3390/rs18152515

BibTeX
@article{Liu2026,
  author = {Liu, Tao and Liu, Qianqian and Zuo, Xiaoyu},
  title = {DyPerceiver-Det: Instance-Wise Dynamic Perception for Fine-Grained Oriented Object Detection in Remote Sensing Images},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {15},
  pages = {2515},
  doi = {10.3390/rs18152515}
}
Kostenlos starten →