Event-based Spiking Neural Networks for Object Detection: A Review of Datasets, Architectures, Learning Rules, and Implementation

TL;DR

This review systematically analyzes datasets, architectures, learning rules, and implementation techniques for event-based spiking neural networks in object detection, highlighting their energy efficiency, performance trade-offs, and future challenges.

Contribution

It provides a comprehensive overview of SNN-based object detection, including analysis of 151 studies, and offers open-source resources for building and evaluating SNN models.

Findings

Fully connected, convolutional, and recurrent architectures are effective.

Different learning methods show trade-offs in accuracy and efficiency.

Neuromorphic hardware implementations balance energy, latency, and memory.

Abstract

Spiking Neural Networks (SNNs) represent a biologically inspired paradigm offering an energy-efficient alternative to conventional artificial neural networks (ANNs) for Computer Vision (CV) applications. This paper presents a systematic review of datasets, architectures, learning methods, implementation techniques, and evaluation methodologies used in CV-based object detection tasks using SNNs. Based on an analysis of 151 journal and conference articles, the review codifies: 1) the effectiveness of fully connected, convolutional, and recurrent architectures; 2) the performance of direct unsupervised, direct supervised, and indirect learning methods; and 3) the trade-offs in energy consumption, latency, and memory in neuromorphic hardware implementations. An open-source repository along with detailed examples of Python code and resources for building SNN models, event-based data processing, and SNN simulations are provided. Key challenges in SNN training, hardware integration, and future directions for CV applications are also identified.