Abstract
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.
Abstract (translated)
基于事件的相机提供了在高动态范围环境和快速运动操作中执行计算机视觉任务可靠的测量。然而,在基于事件的图像处理中采用深度学习面临由于事件相机及时性导致的标注数据短缺的挑战。通过将传统相机的标注数据所获得的知识进行无监督领域适应算法的训练,为解决这个问题提供了一个实用的解决方案。我们开发了一种基于梯度的学习算法,用于训练基于事件的数据处理图像分类深度学习网络,使用对比学习和无相关化数据预处理。我们的解决方案在这个目标上比现有的算法表现更好。
URL
https://arxiv.org/abs/2303.12424
