EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

TL;DR

EventZoom is a novel event data augmentation method for neuromorphic vision that preserves spatial and temporal integrity, improving performance across various learning frameworks in dynamic real-world scenarios.

Contribution

We introduce EventZoom, a progressive augmentation strategy that maintains spatial and temporal features, outperforming existing methods in neuromorphic event data processing.

Findings

EventZoom outperforms existing augmentation methods with state-of-the-art results.

It is effective across supervised, semi-supervised, and unsupervised learning frameworks.

The method preserves key event data characteristics like sparsity and high dynamic range.

Abstract

Dynamic Vision Sensors (DVS) capture event data with high temporal resolution and low power consumption, presenting a more efficient solution for visual processing in dynamic and real-time scenarios compared to conventional video capture methods. Event data augmentation serve as an essential method for overcoming the limitation of scale and diversity in event datasets. Our comparative experiments demonstrate that the two factors, spatial integrity and temporal continuity, can significantly affect the capacity of event data augmentation, which are guarantee for maintaining the sparsity and high dynamic range characteristics unique to event data. However, existing augmentation methods often neglect the preservation of spatial integrity and temporal continuity. To address this, we developed a novel event data augmentation strategy EventZoom, which employs a temporal progressive strategy, embedding transformed samples into the original samples through progressive scaling and shifting. The scaling process avoids the spatial information loss associated with cropping, while the progressive strategy prevents interruptions or abrupt changes in temporal information. We validated EventZoom across various supervised learning frameworks. The experimental results show that EventZoom consistently outperforms existing event data augmentation methods with SOTA performance. For the first time, we have concurrently employed Semi-supervised and Unsupervised learning to verify feasibility on event augmentation algorithms, demonstrating the applicability and effectiveness of EventZoom as a powerful event-based data augmentation tool in handling real-world scenes with high dynamics and variability environments.