标题： 可迁移的多色光学编码器用于神经网络 显示英文标题

标题： Transferable polychromatic optical encoder for neural networks

摘要： 人工神经网络（ANNs）彻底改变了计算机视觉领域，提供了前所未有的性能。 然而，这些用于图像处理的ANNs需要大量的计算资源，通常会阻碍实时操作。 在本文中，我们展示了一种光学编码器，可以在图像捕获期间同时在三个颜色通道中进行卷积，有效地实现了ANN的几个初始卷积层。 这种光学编码导致计算操作减少了约24,000倍，在自由空间光学系统中实现了最先进的分类准确率（约73.2%）。 此外，我们的模拟光学编码器，针对CIFAR-10数据进行训练，可以无需任何修改转移到ImageNet子集High-10，并且仍然表现出中等准确率。 我们的结果证明了混合光学/数字计算机视觉系统的潜力，其中光学前端可以预处理环境场景，以减少整个计算机视觉系统的能耗和延迟。 显示英文摘要

摘要： Artificial neural networks (ANNs) have fundamentally transformed the field of computer vision, providing unprecedented performance. However, these ANNs for image processing demand substantial computational resources, often hindering real-time operation. In this paper, we demonstrate an optical encoder that can perform convolution simultaneously in three color channels during the image capture, effectively implementing several initial convolutional layers of a ANN. Such an optical encoding results in ~24,000 times reduction in computational operations, with a state-of-the art classification accuracy (~73.2%) in free-space optical system. In addition, our analog optical encoder, trained for CIFAR-10 data, can be transferred to the ImageNet subset, High-10, without any modifications, and still exhibits moderate accuracy. Our results evidence the potential of hybrid optical/digital computer vision system in which the optical frontend can pre-process an ambient scene to reduce the energy and latency of the whole computer vision system.