EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BN-SNN: Spiking neural networks with bistable neurons for object detection

Siddiqui Muhammad Yasir iD, Hyun Kim iD

PLOS One · 10.07.2025 · 20 (7) · e0327513

DOI: 10.1371/journal.pone.0327513 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 10.07.2025. Verfasst von Siddiqui Muhammad Yasir und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Information Engineering, Research Center for Electrical and Information Technology, Seoul National University of Science…. Hauptthemen laut MEDLINE: Neural Networks, Computer, Neurons, Action Potentials. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea governmen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spiking neural networks (SNNs) are emerging as a promising evolution in neural network paradigms, offering an alternative to conventional convolutional neural networks (CNNs). One of the most effective methods for SNN development is the CNN-to-SNN conversion process. However, existing conversion techniques are hindered by long temporal durations or inference latencies, which negatively impact the accuracy of the converted networks. Additionally, the application of SNNs in object detection tasks remains largely under-explored. In this study, we propose a novel approach utilizing a bistable integrate-and-fire (BIF) neuron model integrated with a single-shot multibox detector (SSD) as the detection head. Leveraging the proposed BIF neuron framework, we convert the widely used ResNet architecture into an SNN. We validate the effectiveness of our approach through object detection tasks on the MS-COCO and Automotive GEN1 datasets. Experimental results show that our conversion technique facilitates object detection with reduced temporal steps and significant enhancements in mean average precision (mAP), achieving mAP@0.5 scores of 0.476 and 0.591 for the MS-COCO and Automotive GEN1 datasets, respectively. This research marks the first application of BIF neurons to object detection, presenting a novel advancement in the field.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerNeuronsAction PotentialsModels, NeurologicalHumansAlgorithms

Autor:innen und Institutionen

  • Department of Electrical and Information Engineering, Research Center for Electrical and Information Technology, Seoul National University of Science and Technology, Seoul, South Korea.

ORCID-Profile: Siddiqui Muhammad Yasir, Hyun Kim

Förderung

  • Korea governmen

Zitieren

APA

Muhammad Yasir, S., & Kim, H. (2025). BN-SNN: Spiking neural networks with bistable neurons for object detection. PLOS One, 20(7), e0327513. https://doi.org/10.1371/journal.pone.0327513

Vancouver

Muhammad Yasir S, Kim H. BN-SNN: Spiking neural networks with bistable neurons for object detection. PLOS One. 2025;20(7):e0327513. doi:10.1371/journal.pone.0327513

BibTeX
@article{MuhammadYasir2025,
  author = {Muhammad Yasir, Siddiqui and Kim, Hyun},
  title = {BN-SNN: Spiking neural networks with bistable neurons for object detection},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {7},
  pages = {e0327513},
  doi = {10.1371/journal.pone.0327513}
}
Kostenlos starten →