Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection
Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and low-power advantages over Artificial Neural Networks (ANNs). Applications of SNNs are currently limited to simple classification tasks because of their poor performance. In this work, we focus on bridging the performance gap bet...
Saved in:
Main Authors | , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
30.07.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and
low-power advantages over Artificial Neural Networks (ANNs). Applications of
SNNs are currently limited to simple classification tasks because of their poor
performance. In this work, we focus on bridging the performance gap between
ANNs and SNNs on object detection. Our design revolves around network
architecture and spiking neuron. First, the overly complex module design causes
spike degradation when the YOLO series is converted to the corresponding
spiking version. We design a SpikeYOLO architecture to solve this problem by
simplifying the vanilla YOLO and incorporating meta SNN blocks. Second, object
detection is more sensitive to quantization errors in the conversion of
membrane potentials into binary spikes by spiking neurons. To address this
challenge, we design a new spiking neuron that activates Integer values during
training while maintaining spike-driven by extending virtual timesteps during
inference. The proposed method is validated on both static and neuromorphic
object detection datasets. On the static COCO dataset, we obtain 66.2% mAP@50
and 48.9% mAP@50:95, which is +15.0% and +18.7% higher than the prior
state-of-the-art SNN, respectively. On the neuromorphic Gen1 dataset, we
achieve 67.2% mAP@50, which is +2.5% greater than the ANN with equivalent
architecture, and the energy efficiency is improved by 5.7*. Code:
https://github.com/BICLab/SpikeYOLO |
---|---|
DOI: | 10.48550/arxiv.2407.20708 |