Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images

03/04/2022
by   Qianyun Lu, et al.
3

This paper studies the merits of applying log-gradient input images to convolutional neural networks (CNNs) for tinyML computer vision (CV). We show that log gradients enable: (i) aggressive 1.5-bit quantization of first-layer inputs, (ii) potential CNN resource reductions, and (iii) inherent robustness to illumination changes (1.7 variation vs. up to 10 RAW image data set and through a combination of experiments using neural architecture search and a fixed three-layer network. The latter reveal that training on log-gradient images leads to higher filter similarity, making the CNN more prunable. The combined benefits of aggressive first-layer quantization, CNN resource reductions, and operation without tight exposure control and image signal processing (ISP) are helpful for pushing tinyML CV toward its ultimate efficiency limits.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset