为事件相机数据设计多维度增强方法，提升模型鲁棒性。
EventAug: Multifaceted Spatio-Temporal Data Augmentation Methods for Event-based Learning
- 通过多尺度时间融合调节物体运动速度多样性
- 引入空间与时间显著掩码丰富物体形态变化
- 在多个任务上提升准确率，适合事件视觉研究者
事件相机因其低延迟和高动态范围，在多个领域表现出色。然而，数据不足与多样性匮乏导致过拟合和特征学习不充分，且事件领域数据增强研究仍较匮乏。本文提出系统性增强方案EventAug，以丰富时空多样性。首先提出多尺度时间融合（MSTI）以多样化物体运动速度；随后引入空间显著事件掩码（SSEM）和时间显著事件掩码（TSEM）以增强物体变体。该方法促进模型学习更丰富的运动模式、物体变体及局部时空关系，从而提升对不同运动速度、遮挡和动作干扰的鲁棒性。实验表明，该方法在多种任务和骨干网络上均取得显著提升（如在DVS128 Gesture数据集上提升4.87%准确率）。代码将公开共享。
原文摘要 · Abstract (English)
The event camera has demonstrated significant success across a wide range of areas due to its low time latency and high dynamic range. However, the community faces challenges such as data deficiency and limited diversity, often resulting in over-fitting and inadequate feature learning. Notably, the exploration of data augmentation techniques in the event community remains scarce. This work aims to address this gap by introducing a systematic augmentation scheme named EventAug to enrich spatial-temporal diversity. In particular, we first propose Multi-scale Temporal Integration (MSTI) to diversify the motion speed of objects, then introduce Spatial-salient Event Mask (SSEM) and Temporal-salient Event Mask (TSEM) to enrich object variants. Our EventAug can facilitate models learning with richer motion patterns, object variants and local spatio-temporal relations, thus improving model robustness to varied moving speeds, occlusions, and action disruptions. Experiment results show that our augmentation method consistently yields significant improvements across different tasks and backbones (e.g., a 4.87% accuracy gain on DVS128 Gesture). Our code will be publicly available for this community.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。