EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatial–Frequency Inductive Bias-Guided Cross-Domain Representation Learning for Infrared Small Object Detection

Quanrun Cheng, Cao Zeng, Qi He, Yuhong Zhang, Hailong Ning

Remote Sensing · 20.05.2026 · 18 (10) · 1645

DOI: 10.3390/rs18101645 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 20.05.2026. Verfasst von Quanrun Cheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 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)

Infrared small object detection (ISOD) plays a crucial role in military reconnaissance, security surveillance, and remote sensing monitoring, where weak thermal responses and complex backgrounds impose significant challenges. The recent self-supervised vision foundation model DINOv3 has demonstrated remarkable generalization ability across various visual tasks. However, directly transferring it to ISOD still remains challenging due to substantial cross-domain discrepancy between visible and infrared imagery, as well as the limited granularity of foundation features in capturing subtle thermal variations. To address these issues, this study proposes a spatial–frequency inductive bias-guided network (SFI-Net) based on DINOv3 for cross-domain representation learning in infrared small object detection. Instead of conventional domain adaptation strategies, SFI-Net explicitly models infrared-specific inductive biases in both spatial and frequency domains to enhance transferred representations. First, a spatio-frequency hybrid adapter (SFHA) is designed and embedded across multiple layers of the frozen backbone to learn infrared-specific inductive biases within distinct subspaces. Second, a feature compensation strategy with an auxiliary convolutional branch is devised to compensate for the limitation of DINOv3 in capturing multi-scale fine-grained features. Extensive experiments on the IRSTD-1K and NUDT-SIRST datasets demonstrate that the proposed SFI-Net outperforms state-of-the-art methods in both detection accuracy and computational efficiency while exhibiting strong cross-scenario generalization capability.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cheng, Q., Zeng, C., He, Q., Zhang, Y., & Ning, H. (2026). Spatial–Frequency Inductive Bias-Guided Cross-Domain Representation Learning for Infrared Small Object Detection. Remote Sensing, 18(10), 1645. https://doi.org/10.3390/rs18101645

Vancouver

Cheng Q, Zeng C, He Q, Zhang Y, Ning H. Spatial–Frequency Inductive Bias-Guided Cross-Domain Representation Learning for Infrared Small Object Detection. Remote Sensing. 2026;18(10):1645. doi:10.3390/rs18101645

BibTeX
@article{Cheng2026,
  author = {Cheng, Quanrun and Zeng, Cao and He, Qi and Zhang, Yuhong and Ning, Hailong},
  title = {Spatial–Frequency Inductive Bias-Guided Cross-Domain Representation Learning for Infrared Small Object Detection},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1645},
  doi = {10.3390/rs18101645}
}
Kostenlos starten →