# EventMix: An Efficient Augmentation Strategy for Event-Based Data

arXiv: https://arxiv.org/abs/2205.12054 · HTML: https://mlsanity.com/paper/2205.12054/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2022.

## Built on by (most cited first, 6 of 6)

- [Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2211.10686/) (2022)
- [Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Network](https://mlsanity.com/paper/2401.01912/) (2024)
- [TIM: An Efficient Temporal Interaction Module for Spiking Transformer](https://mlsanity.com/paper/2401.11687/) (2024)
- [Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future](https://mlsanity.com/paper/2304.06540/) (2023)
- [An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain](https://mlsanity.com/paper/2303.13077/) (2023)
- [A Spatial-channel-temporal-fused Attention for Spiking Neural Networks](https://mlsanity.com/paper/2209.10837/) (2022)

## Abstract (arXiv)

High-quality and challenging event stream datasets play an important role in the design of an efficient event-driven mechanism that mimics the brain. Although event cameras can provide high dynamic range and low-energy event stream data, the scale is smaller and more difficult to obtain than traditional frame-based data, which restricts the development of neuromorphic computing. Data augmentation can improve the quantity and quality of the original data by processing more representations from the original data. This paper proposes an efficient data augmentation strategy for event stream data: EventMix. We carefully design the mixing of different event streams by Gaussian Mixture Model to generate random 3D masks and achieve arbitrary shape mixing of event streams in the spatio-temporal dimension. By computing the relative distances of event streams, we propose a more reasonable way to assign labels to the mixed samples. The experimental results on multiple neuromorphic datasets have shown that our strategy can improve its performance on neuromorphic datasets both for ANNs and SNNs, and we have achieved state-of-the-art performance on DVS-CIFAR10, N-Caltech101, N-CARS, and DVS-Gesture datasets.