A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism

TL;DR

This paper introduces a novel DVS object recognition model that employs trainable event-driven convolution and a spiking attention mechanism, enhancing feature extraction and classification accuracy over traditional methods.

Contribution

It proposes a trainable event-driven convolution kernel updated via gradient descent and integrates a spiking attention mechanism for improved global feature extraction.

Findings

Outperforms baseline methods on MNIST-DVS and CIFAR10-DVS datasets.

Shows strong classification performance on short event streams.

Enhances feature extraction capabilities of SNNs for DVS objects.

Abstract

Spiking Neural Networks (SNNs) are well-suited for processing event streams from Dynamic Visual Sensors (DVSs) due to their use of sparse spike-based coding and asynchronous event-driven computation. To extract features from DVS objects, SNNs commonly use event-driven convolution with fixed kernel parameters. These filters respond strongly to features in specific orientations while disregarding others, leading to incomplete feature extraction. To improve the current event-driven convolution feature extraction capability of SNNs, we propose a DVS object recognition model that utilizes a trainable event-driven convolution and a spiking attention mechanism. The trainable event-driven convolution is proposed in this paper to update its convolution kernel through gradient descent. This method can extract local features of the event stream more efficiently than traditional event-driven convolution. Furthermore, the spiking attention mechanism is used to extract global dependence features. The classification performances of our model are better than the baseline methods on two neuromorphic datasets including MNIST-DVS and the more complex CIFAR10-DVS. Moreover, our model showed good classification ability for short event streams. It was shown that our model can improve the performance of event-driven convolutional SNNs for DVS objects.