English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Spiking Neural Networks (SNNs) are a biologically plausible neural networkmodel with significant advantages in both event-driven processing andspatio-temporal information processing, rendering SNNs an appealing choice forenergyefficient object detection. However, the non-differentiability of thebiological neuronal dynamics model presents a challenge during the training ofSNNs. Furthermore, a suitable decoding strategy for object detection in SNNs iscurrently lacking. In this study, we introduce the Current Mean Decoding (CMD)method, which solves the regression problem to facilitate the training of deepSNNs for object detection tasks. Based on the gradient surrogate and CMD, wepropose the SNN-YOLOv3 model for object detection. Our experiments demonstratethat SNN-YOLOv3 achieves a remarkable performance with an mAP of 61.87% on thePASCAL VOC dataset, requiring only 6 time steps. Compared to SpikingYOLO, wehave managed to increase mAP by nearly 10% while reducing energy consumption bytwo orders of magnitude.

Enabling energy-Efficient object detection with surrogate gradient descent in spiking neural networks