Spiking Neural Networks for Visual Place Recognition via Weighted Neuronal Assignments

TL;DR

This paper presents a novel high-performance spiking neural network for visual place recognition, utilizing a weighted neuronal assignment scheme to improve accuracy and robustness while maintaining energy efficiency.

Contribution

It introduces a new SNN architecture with a weighted assignment scheme for ambiguity-informed salience, specifically designed for visual place recognition tasks.

Findings

Achieves comparable performance to state-of-the-art methods on multiple datasets.

Degrades gracefully as the number of reference places increases.

Provides a step towards robust, energy-efficient robot localization.

Abstract

Spiking neural networks (SNNs) offer both compelling potential advantages, including energy efficiency and low latencies and challenges including the non-differentiable nature of event spikes. Much of the initial research in this area has converted deep neural networks to equivalent SNNs, but this conversion approach potentially negates some of the advantages of SNN-based approaches developed from scratch. One promising area for high-performance SNNs is template matching and image recognition. This research introduces the first high-performance SNN for the Visual Place Recognition (VPR) task: given a query image, the SNN has to find the closest match out of a list of reference images. At the core of this new system is a novel assignment scheme that implements a form of ambiguity-informed salience, by up-weighting single-place-encoding neurons and down-weighting "ambiguous" neurons that respond to multiple different reference places. In a range of experiments on the challenging Nordland, Oxford RobotCar, SPEDTest, Synthia, and St Lucia datasets, we show that our SNN achieves comparable VPR performance to state-of-the-art and classical techniques, and degrades gracefully in performance with an increasing number of reference places. Our results provide a significant milestone towards SNNs that can provide robust, energy-efficient, and low latency robot localization.