Spike-EVPR: Deep Spiking Residual Networks with SNN-Tailored Representations for Event-Based Visual Place Recognition

TL;DR

This paper introduces Spike-EVPR, a novel deep spiking residual network with tailored event representations for energy-efficient visual place recognition using event cameras, achieving state-of-the-art results.

Contribution

It proposes two new event representations and a deep spiking residual architecture for end-to-end training of SNNs in VPR tasks, addressing previous limitations.

Findings

Achieves state-of-the-art performance on Brisbane-Event-VPR and DDD20 datasets.

Improves Recall@1 by 7.61% and 13.20% respectively.

Reduces energy consumption significantly.

Abstract

Event cameras are ideal for visual place recognition (VPR) in challenging environments due to their high temporal resolution and high dynamic range. However, existing methods convert sparse events into dense frame-like representations for Artificial Neural Networks (ANNs), ignoring event sparsity and incurring high computational cost. Spiking Neural Networks (SNNs) complement event data through discrete spike signals to enable energy-efficient VPR, but their application is hindered by the lack of effective spike-compatible representations and deep architectures capable of learning discriminative global descriptors. To address these limitations, we propose Spike-EVPR, a directly trained, end-to-end SNN framework tailored for event-based VPR. First, we introduce two complementary event representations, MCS-Tensor and TSS-Tensor, designed to reduce temporal redundancy while preserving essential spatio-temporal cues. Furthermore, we propose a deep spiking residual architecture that effectively aggregates these features to generate robust place descriptors. Extensive experiments on the Brisbane-Event-VPR and DDD20 datasets demonstrate that Spike-EVPR achieves state-of-the-art performance, improving Recall@1 by 7.61% and 13.20%, respectively, while significantly reducing energy consumption.