EUVIMEDEUVIMED entdecken
Crossref

Spiking Neural Networks With Adaptive Membrane Time Constant for Event-Based Tracking

Jiqing Zhang, Malu Zhang, Yuanchen Wang, Qianhui Liu, Baocai Yin, Haizhou Li, Xin Yang

IEEE Transactions on Image Processing · 2025 · 34 · 1009-1021

DOI: 10.1109/tip.2025.3533213 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Jiqing Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 88 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Distinguished Young Scholars Funding of Dalian.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The brain-inspired Spiking Neural Networks (SNNs) work in an event-driven manner and have an implicit recurrence in neuronal membrane potential to memorize information over time, which are inherently suitable to handle temporal event-based streams. Despite their temporal nature and recent approaches advancements, these methods have predominantly been assessed on event-based classification tasks. In this paper, we explore the utility of SNNs for event-based tracking tasks. Specifically, we propose a brain-inspired adaptive Leaky Integrate-and-Fire neuron (BA-LIF) that can adaptively adjust the membrane time constant according to the inputs, thereby accelerating the leakage of meaningless noise features and reducing the decay of valuable information. SNNs composed of our proposed BA-LIF neurons can achieve high performance without a careful and time-consuming trial-by-error initialization on the membrane time constant. The adaptive capability of our network is further improved by introducing an extra temporal feature aggregator (TFA) that assigns attention weights over the temporal dimension. Extensive experiments on various event-based tracking datasets validate the effectiveness of our proposed method. We further validate the generalization capability of our method by applying it to other event-classification tasks.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Distinguished Young Scholars Funding of Dalian
  • Sichuan Science and Technology Program
  • China Postdoctoral Science Foundation
  • Chinese Scholarship Council (CSC) Grant

Zitieren

APA

Zhang, J., Zhang, M., Wang, Y., Liu, Q., Yin, B., Li, H., & Yang, X. (2025). Spiking Neural Networks With Adaptive Membrane Time Constant for Event-Based Tracking. IEEE Transactions on Image Processing, 34, 1009-1021. https://doi.org/10.1109/tip.2025.3533213

Vancouver

Zhang J, Zhang M, Wang Y, Liu Q, Yin B, Li H, et al. Spiking Neural Networks With Adaptive Membrane Time Constant for Event-Based Tracking. IEEE Transactions on Image Processing. 2025;34:1009-1021. doi:10.1109/tip.2025.3533213

BibTeX
@article{Zhang2025,
  author = {Zhang, Jiqing and Zhang, Malu and Wang, Yuanchen and Liu, Qianhui and Yin, Baocai and Li, Haizhou and Yang, Xin},
  title = {Spiking Neural Networks With Adaptive Membrane Time Constant for Event-Based Tracking},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {1009--1021},
  doi = {10.1109/tip.2025.3533213}
}
Kostenlos starten →