EUVIMEDEUVIMED entdecken
Crossref

Efficient event-based object detection with lightweight CNNs: a surprising advantage over transformers

Sen Zhang, Pengfei Wang, Yaofeng Cheng, Xiangji Wang, Xiuwen Bi, Fusheng Zha, Mantian Li, Lining Sun

Applied Optics · 10.04.2026 · 65 (11) · 3748

DOI: 10.1364/ao.590967 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Optics, online erschienen am 08.04.2026. Verfasst von Sen Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Major Internal Cultivation Project of Harbin Institute of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Achieving robust robotic perception in highly dynamic environments requires accurate and low-latency visual object detection. However, conventional RGB cameras often exhibit limited performance in such fast-changing scenarios due to significant blind time, imaging latency, and motion blur. In this context, event cameras have emerged as a promising solution, offering microsecond-level temporal resolution, high dynamic range, and immunity to motion blur. However, despite these significant theoretical advantages, algorithms for event cameras are still at a nascent stage. Existing approaches, including both transformers and traditional CNNs, struggle to achieve high accuracy and low latency simultaneously, thereby limiting their effectiveness for object detection in highly dynamic environments. Notably, recent studies such as ConvNeXt suggest that modernized CNNs can outperform both vision transformers and traditional CNNs by adopting transformer-like architectural designs. Motivated by this insight, we propose a lightweight CNN-based object detection model, EvConvLite. By strategically “modernizing” the traditional CNNs, our model not only achieves 3× inference speedup, but also surpasses state-of-the-art transformer-based models in detection accuracy. To the best of our knowledge, this is the first reported instance of a lightweight CNN-based model outperforming transformers in event camera object detection accuracy.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Major Internal Cultivation Project of Harbin Institute of Technology
  • National Independent Project of China
  • Key Technology Research and Development of Suzhou
  • School Enterprise Joint Research and Development Center for Cemented Carbide Cutting Tools of Shenzhen Polytechnic University

Zitieren

APA

Zhang, S., Wang, P., Cheng, Y., Wang, X., Bi, X., Zha, F., Li, M., & Sun, L. (2026). Efficient event-based object detection with lightweight CNNs: a surprising advantage over transformers. Applied Optics, 65(11), 3748. https://doi.org/10.1364/ao.590967

Vancouver

Zhang S, Wang P, Cheng Y, Wang X, Bi X, Zha F, et al. Efficient event-based object detection with lightweight CNNs: a surprising advantage over transformers. Applied Optics. 2026;65(11):3748. doi:10.1364/ao.590967

BibTeX
@article{Zhang2026,
  author = {Zhang, Sen and Wang, Pengfei and Cheng, Yaofeng and Wang, Xiangji and Bi, Xiuwen and Zha, Fusheng and Li, Mantian and Sun, Lining},
  title = {Efficient event-based object detection with lightweight CNNs: a surprising advantage over transformers},
  journal = {Applied Optics},
  year = {2026},
  volume = {65},
  number = {11},
  pages = {3748},
  doi = {10.1364/ao.590967}
}
Kostenlos starten →