ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks using Angle Sensitive Pixels

Abstract

Deep learning using convolutional neural networks (CNNs) is quickly becoming the state-of-the-art for challenging computer vision applications. However, deep learning's power consumption and bandwidth requirements currently limit its application in embedded and mobile systems with tight energy budgets. In this paper, we explore the energy savings of optically computing the first layer of CNNs. To do so, we utilize bio-inspired Angle Sensitive Pixels (ASPs), custom CMOS diffractive image sensors which act similar to Gabor filter banks in the V1 layer of the human visual cortex. ASPs replace both image sensing and the first layer of a conventional CNN by directly performing optical edge filtering, saving sensing energy, data bandwidth, and CNN FLOPS to compute. Our experimental results (both on synthetic data and a hardware prototype) for a variety of vision tasks such as digit recognition, object recognition, and face identification demonstrate using ASPs while achieving similar performance compared to traditional deep learning pipelines.

Presented in CVPR 2016 (oral), 10 pages, 12 figures. This new version corrects the comparison between imaging power for ASPs and a regular image sensor

References in corpus (8)

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Going Deeper with Convolutions
• Compressing Deep Convolutional Networks using Vector Quantization
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Neural Networks with Few Multiplications
• Convolutional Sparse Coding for High Dynamic Range Imaging
• Compressing Convolutional Neural Networks
• Towards Trainable Media: Using Waves for Neural Network-Style Training