Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection

TL;DR

This paper introduces Spiking-YOLO, a novel spiking neural network model for object detection that achieves high accuracy with significantly reduced energy consumption and faster convergence compared to traditional deep neural networks.

Contribution

The paper presents the first spiking neural network model for object detection, introducing two novel methods to improve deep SNN performance and demonstrating its effectiveness on challenging datasets.

Findings

Achieves up to 98% accuracy of Tiny YOLO on PASCAL VOC and MS COCO.

Consumes approximately 280 times less energy than Tiny YOLO on neuromorphic hardware.

Converges 2.3 to 4 times faster than previous SNN conversion techniques.

Abstract

Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-generation of neural networks due to their event-driven and low-powered nature. SNNs, however, are difficult to train, mainly owing to their complex dynamics of neurons and non-differentiable spike operations. Furthermore, their applications have been limited to relatively simple tasks such as image classification. In this study, we investigate the performance degradation of SNNs in a more challenging regression problem (i.e., object detection). Through our in-depth analysis, we introduce two novel methods: channel-wise normalization and signed neuron with imbalanced threshold, both of which provide fast and accurate information transmission for deep SNNs. Consequently, we present a first spiked-based object detection model, called Spiking-YOLO. Our experiments show that Spiking-YOLO achieves remarkable results that are comparable (up to 98%) to those of Tiny YOLO on non-trivial datasets, PASCAL VOC and MS COCO. Furthermore, Spiking-YOLO on a neuromorphic chip consumes approximately 280 times less energy than Tiny YOLO and converges 2.3 to 4 times faster than previous SNN conversion methods.