When Spiking neural networks meet temporal attention image decoding and adaptive spiking neuron

TL;DR

This paper introduces a novel image decoding method using temporal attention and adaptive spiking neurons, significantly improving image quality and classification accuracy in spiking neural networks.

Contribution

It proposes a new temporal attention-based image decoding method and an adaptive neuron model that enhances SNN performance and learning capabilities.

Findings

Outperforms state-of-the-art in image decoding metrics.

Achieves 99.78% accuracy on MNIST.

Achieves 93.89% accuracy on CIFAR-10.

Abstract

Spiking Neural Networks (SNNs) are capable of encoding and processing temporal information in a biologically plausible way. However, most existing SNN-based methods for image tasks do not fully exploit this feature. Moreover, they often overlook the role of adaptive threshold in spiking neurons, which can enhance their dynamic behavior and learning ability. To address these issues, we propose a novel method for image decoding based on temporal attention (TAID) and an adaptive Leaky-Integrate-and-Fire (ALIF) neuron model. Our method leverages the temporal information of SNN outputs to generate high-quality images that surpass the state-of-the-art (SOTA) in terms of Inception score, Fr\'echet Inception Distance, and Fr\'echet Autoencoder Distance. Furthermore, our ALIF neuron model achieves remarkable classification accuracy on MNIST (99.78\%) and CIFAR-10 (93.89\%) datasets, demonstrating the effectiveness of learning adaptive thresholds for spiking neurons. The code is available at https://github.com/bollossom/ICLR_TINY_SNN.