Neural information coding for efficient spike-based image denoising
This addresses the problem of computational inefficiency for embedded and mobile devices in image restoration, though it is incremental as it builds on existing SNN methods.
The paper tackled image denoising using Spiking Neural Networks (SNNs) to reduce computational costs compared to Deep Convolutional Neural Networks (DCNNs), achieving competitive denoising performance with lower computational load.
In recent years, Deep Convolutional Neural Networks (DCNNs) have outreached the performance of classical algorithms for image restoration tasks. However most of these methods are not suited for computational efficiency and are therefore too expensive to be executed on embedded and mobile devices. In this work we investigate Spiking Neural Networks (SNNs) for Gaussian denoising, with the goal of approaching the performance of conventional DCNN while reducing the computational load. We propose a formal analysis of the information conversion processing carried out by the Leaky Integrate and Fire (LIF) neurons and we compare its performance with the classical rate-coding mechanism. The neural coding schemes are then evaluated through experiments in terms of denoising performance and computation efficiency for a state-of-the-art deep convolutional neural network. Our results show that SNNs with LIF neurons can provide competitive denoising performance but at a reduced computational cost.