IVCVMar 4, 2022

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

arXiv:2203.02571v17 citationsh-index: 53
Originality Incremental advance
AI Analysis

This work addresses efficiency and robustness challenges for tinyML computer vision applications, representing an incremental improvement with specific gains.

This paper tackles the problem of improving energy efficiency and robustness in tinyML computer vision by applying log-gradient input images to CNNs, enabling aggressive 1.5-bit quantization of first-layer inputs and reducing accuracy loss to 1.7% across brightness variations compared to up to 10% for JPEG.

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% accuracy loss across 1/32...8 brightness variation vs. up to 10% for JPEG). We establish these results using the PASCAL 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes