Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated data scarcity due to recency of event cameras. Transferring the knowledge that can be obtained from conventional camera annotated data offers a practical solution to this challenge. We develop an unsupervised domain adaptation algorithm for training a deep network for event-based data image classification using contrastive learning and uncorrelated conditioning of data. Our solution outperforms the existing algorithms for this purpose.

翻译：事件相机在高动态范围环境及快速运动场景下为计算机视觉任务提供了可靠的测量手段。然而，由于事件相机的问世时间较晚，深度学习方法在事件视觉中面临标注数据稀缺的挑战。利用传统相机标注数据的知识迁移为解决该问题提供了可行方案。本文提出一种无监督域适应算法，通过对比学习与数据解相关条件约束，训练用于事件数据图像分类的深度网络。实验结果表明，本方法在该领域显著优于现有算法。