EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spectra-Net: Frequency-Aware Scale Adaptation for Small Object Detection

Yang Xu, Kaiwang Wang, Donglin Yang, Guanqiu Qi, Kunpeng Wang, Shuang Li

Algorithms · 27.07.2026 · 19 (8) · 628

DOI: 10.3390/a19080628 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 27.07.2026. Verfasst von Yang Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program, Chongqing Municipality Education Commission, Science and Technology Innovation Key R&D Program of Chongqing.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small object detection in real-world scenarios remains challenging due to two coupled factors: severe scale imbalance and progressive degradation of fine-grained cues during backbone downsampling. Under drastic scale variations, conventional detectors still rely on static backbones whose fixed convolutional responses cannot consistently accommodate the divergent spectral characteristics of large and tiny objects, leading to scale-mismatched representations. Meanwhile, repeated strided operations reduce the sampling rate of feature maps and tend to introduce aliasing, eroding the high-frequency details that are critical for tiny objects. To address these issues, we propose Spectra-Net, a novel frequency-aware detection framework that redesigns backbone feature encoding with explicit spectral control. At its core, we introduce Dynamic Fourier Alignment (DFA), which performs content-adaptive yet frequency-controllable modulation to reshape convolutional responses in the spectral domain, aligning representations across scales and amplifying discriminative cues for small objects. In addition, we develop Wavelet-Guided Spectral Downsampling (WGSD), which conducts explicit sub-band decomposition via Haar wavelets to suppress aliasing while selectively preserving informative high-frequency components during resolution reduction. Extensive experiments on VisDrone-2019 and TT100K, together with comprehensive ablations, demonstrate that Spectra-Net consistently improves small object detection performance under severe scale imbalance.

Förderung

  • Sichuan Science and Technology Program
  • Chongqing Municipality Education Commission
  • Science and Technology Innovation Key R&D Program of Chongqing
  • Central Government Program for Guiding Local Regional Innovation System Development Project

Zitieren

APA

Xu, Y., Wang, K., Yang, D., Qi, G., Wang, K., & Li, S. (2026). Spectra-Net: Frequency-Aware Scale Adaptation for Small Object Detection. Algorithms, 19(8), 628. https://doi.org/10.3390/a19080628

Vancouver

Xu Y, Wang K, Yang D, Qi G, Wang K, Li S. Spectra-Net: Frequency-Aware Scale Adaptation for Small Object Detection. Algorithms. 2026;19(8):628. doi:10.3390/a19080628

BibTeX
@article{Xu2026,
  author = {Xu, Yang and Wang, Kaiwang and Yang, Donglin and Qi, Guanqiu and Wang, Kunpeng and Li, Shuang},
  title = {Spectra-Net: Frequency-Aware Scale Adaptation for Small Object Detection},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {8},
  pages = {628},
  doi = {10.3390/a19080628}
}
Kostenlos starten →