EventRPG: Event Data Augmentation with Relevance Propagation Guidance
This addresses overfitting in SNNs for event camera data, which is an incremental improvement in a domain-specific area.
The paper tackles overfitting in event-based classification tasks for Spiking Neural Networks (SNNs) by proposing EventRPG, a data augmentation method that uses relevance propagation to generate saliency maps, achieving state-of-the-art accuracies of 85.62% on N-Caltech101, 85.55% on CIFAR10-DVS, and 91.59% on SL-Animals.
Event camera, a novel bio-inspired vision sensor, has drawn a lot of attention for its low latency, low power consumption, and high dynamic range. Currently, overfitting remains a critical problem in event-based classification tasks for Spiking Neural Network (SNN) due to its relatively weak spatial representation capability. Data augmentation is a simple but efficient method to alleviate overfitting and improve the generalization ability of neural networks, and saliency-based augmentation methods are proven to be effective in the image processing field. However, there is no approach available for extracting saliency maps from SNNs. Therefore, for the first time, we present Spiking Layer-Time-wise Relevance Propagation rule (SLTRP) and Spiking Layer-wise Relevance Propagation rule (SLRP) in order for SNN to generate stable and accurate CAMs and saliency maps. Based on this, we propose EventRPG, which leverages relevance propagation on the spiking neural network for more efficient augmentation. Our proposed method has been evaluated on several SNN structures, achieving state-of-the-art performance in object recognition tasks including N-Caltech101, CIFAR10-DVS, with accuracies of 85.62% and 85.55%, as well as action recognition task SL-Animals with an accuracy of 91.59%. Our code is available at https://github.com/myuansun/EventRPG.