Neuromorphic Data Augmentation for Training Spiking Neural Networks

2022/03/11 by Youngeun Kim, Li, Yuhang, Kim, Youngeun +5 · 7 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Neural Networks and Reservoir Computing

paper · pdf · doi:10.48550/arxiv.2203.06145

openalex publication_date 2022/03/11 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28

Abstract

Developing neuromorphic intelligence on event-based datasets with Spiking Neural Networks (SNNs) has recently attracted much research attention. However, the limited size of event-based datasets makes SNNs prone to overfitting and unstable convergence. This issue remains unexplored by previous academic works. In an effort to minimize this generalization gap, we propose Neuromorphic Data Augmentation (NDA), a family of geometric augmentations specifically designed for event-based datasets with the goal of significantly stabilizing the SNN training and reducing the generalization gap between training and test performance. The proposed method is simple and compatible with existing SNN training pipelines. Using the proposed augmentation, for the first time, we demonstrate the feasibility of unsupervised contrastive learning for SNNs. We conduct comprehensive experiments on prevailing neuromorphic vision benchmarks and show that NDA yields substantial improvements over previous state-of-the-art results. For example, the NDA-based SNN achieves accuracy gain on CIFAR10-DVS and N-Caltech 101 by 10.1% and 13.7%, respectively. Code is available on GitHub https://github.com/Intelligent-Computing-Lab-Yale/NDA_SNN

Cited by

• Improving Low-Latency Learning Performance in Spiking Neural Networks via a Change-Perceptive Dendrite-Soma-Axon Neuron
• Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
• Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain
• Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
• Benchmarking Microsaccade Recognition with Event Cameras: A Novel Dataset and Evaluation
• SpikePool: Event-driven Spiking Transformer with Pooling Attention
• Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain

Related

• Training Robust Spiking Neural Networks on Neuromorphic Data with Spatiotemporal Fragments
• NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks
• Training Robust Spiking Neural Networks with ViewPoint Transform and SpatioTemporal Stretching
• An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain
• Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences