# Closing the Accuracy Gap in an Event-Based Visual Recognition Task

arXiv: https://arxiv.org/abs/1906.08859 · HTML: https://mlsanity.com/paper/1906.08859/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2019.

## Built on by (most cited first, 6 of 6)

- [Emergent Visual Sensors for Autonomous Vehicles](https://mlsanity.com/paper/2205.09383/) (2022)
- [Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff](https://mlsanity.com/paper/2301.09522/) (2023)
- [A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data](https://mlsanity.com/paper/2404.03493/) (2024)
- [SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents](https://mlsanity.com/paper/2404.09331/) (2024)
- [Razor SNN: Efficient Spiking Neural Network with Temporal Embeddings](https://mlsanity.com/paper/2306.17597/) (2023)
- [FastSpiker: Enabling Fast Training for Spiking Neural Networks on Event-based Data through Learning Rate Enhancements for Autonomous Embedded Systems](https://mlsanity.com/paper/2407.05262/) (2024)

## Abstract (arXiv)

Mobile and embedded applications require neural networks-based pattern recognition systems to perform well under a tight computational budget. In contrast to commonly used synchronous, frame-based vision systems and CNNs, asynchronous, spiking neural networks driven by event-based visual input respond with low latency to sparse, salient features in the input, leading to high efficiency at run-time. The discrete nature of the event-based data streams makes direct training of asynchronous neural networks challenging. This paper studies asynchronous spiking neural networks, obtained by conversion from a conventional CNN trained on frame-based data. As an example, we consider a CNN trained to steer a robot to follow a moving target. We identify possible pitfalls of the conversion and demonstrate how the proposed solutions bring the classification accuracy of the asynchronous network to only 3% below the performance of the original synchronous CNN, while requiring 12x fewer computations. While being applied to a simple task, this work is an important step towards low-power, fast, and embedded neural networks-based vision solutions for robotic applications.