论文标题
EventMix：基于事件数据的有效增强策略
EventMix: An Efficient Augmentation Strategy for Event-Based Data
论文作者
论文摘要
高质量且具有挑战性的事件流数据集在模拟大脑的高效事件驱动机制的设计中起着重要作用。尽管事件摄像机可以提供高动态范围和低能事件流数据，但比传统基于框架的数据限制了神经形态计算的开发。数据增强可以通过处理原始数据的更多表示形式来提高原始数据的数量和质量。本文提出了事件流数据的有效数据增强策略：EventMix。我们通过高斯混合模型仔细设计了不同事件流的混合，以生成随机的3D掩码，并在时空维度中实现事件流的任意形状混合。通过计算事件流的相对距离，我们提出了一种将标签分配给混合样品的更合理的方法。多个神经形态数据集的实验结果表明，我们的策略可以提高其在ANN和SNN的神经形态数据集上的性能，并且我们在DVS-CIFAR10，N-CALTECH101，N-CARS，N-CARS，N-CARS和DVS-GETURE数据集上实现了最先进的性能。
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.
