EUVIMEDEUVIMED entdecken
Crossref

Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection

Jiangnan Yang, Shuangli Liu, Jingjun Wu, Xinyu Su, Nan Hai, Xueli Huang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (9) · 9202-9210

DOI: 10.1609/aaai.v39i9.32996 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Jiangnan Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 241-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

These recent years have witnessed that convolutional neural network (CNN)-based methods for detecting infrared small targets have achieved outstanding performance. However, these methods typically employ standard convolutions, neglecting to consider the spatial characteristics of the pixel distribution of infrared small targets. Therefore, we propose a novel pinwheel-shaped convolution (PConv) as a replacement for standard convolutions in the lower layers of the backbone network. PConv better aligns with the Gaussian-like spatial distribution of infrared small target, improves feature extraction, significantly expands the receptive field, and introduces only a minimal increase in parameters. Additionally, while recent loss functions combine scale and location losses, they do not adequately account for the varying sensitivity of these losses across different target scales, limiting detection performance on dim-small targets. To overcome this, we propose a scale-based dynamic (SD) Loss that dynamically adjusts the influence of scale and location losses based on target size, improving the network's ability to detect targets of varying scales. We construct a new benchmark, SIRST-UAVB, which is the largest and most challenging dataset to date for real-shot single-frame infrared small target detection. Lastly, by integrating PConv and SD Loss into the latest small target detection algorithms, we achieved significant performance improvements on IRSTD-1K and our SIRST-UAVB dataset, validating the effectiveness and generalizability of our approach.

Zitieren

APA

Yang, J., Liu, S., Wu, J., Su, X., Hai, N., & Huang, X. (2025). Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 9202-9210. https://doi.org/10.1609/aaai.v39i9.32996

Vancouver

Yang J, Liu S, Wu J, Su X, Hai N, Huang X. Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(9):9202-9210. doi:10.1609/aaai.v39i9.32996

BibTeX
@article{Yang2025,
  author = {Yang, Jiangnan and Liu, Shuangli and Wu, Jingjun and Su, Xinyu and Hai, Nan and Huang, Xueli},
  title = {Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {9},
  pages = {9202--9210},
  doi = {10.1609/aaai.v39i9.32996}
}
Kostenlos starten →