Deep Spiking Convolutional Neural Network for Single Object Localization Based On Deep Continuous Local Learning

TL;DR

This paper introduces a deep convolutional spiking neural network utilizing local surrogate gradient learning for object localization, marking progress in applying neuromorphic hardware to complex vision tasks.

Contribution

It presents the first deep spiking neural network for object localization using supervised learning with DECOLLE, advancing neuromorphic vision applications.

Findings

Validated on Oxford-IIIT-Pet dataset

Demonstrated feasibility of supervised deep spiking networks for object localization

Showed potential for complex vision tasks with neuromorphic hardware

Abstract

With the advent of neuromorphic hardware, spiking neural networks can be a good energy-efficient alternative to artificial neural networks. However, the use of spiking neural networks to perform computer vision tasks remains limited, mainly focusing on simple tasks such as digit recognition. It remains hard to deal with more complex tasks (e.g. segmentation, object detection) due to the small number of works on deep spiking neural networks for these tasks. The objective of this paper is to make the first step towards modern computer vision with supervised spiking neural networks. We propose a deep convolutional spiking neural network for the localization of a single object in a grayscale image. We propose a network based on DECOLLE, a spiking model that enables local surrogate gradient-based learning. The encouraging results reported on Oxford-IIIT-Pet validates the exploitation of spiking neural networks with a supervised learning approach for more elaborate vision tasks in the future.