论文标题
部分可观测时空混沌系统的无模型预测
Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images
论文作者
论文摘要
本文研究了将对数级别输入图像应用于卷积神经网络（CNN）的优点，以进行Tinyml计算机视觉（CV）。我们显示对数梯度的启用：（i）对第一层输入，（ii）潜在的CNN资源降低和（iii）照明变化的固有鲁棒性的攻击性1.5位量化（1/32 ... 8亮度变化的精度损失为1.7％vs. jpeg最高10％）。我们使用Pascal原始图像数据集以及使用神经体系结构搜索和固定的三层网络的实验组合来建立这些结果。后者表明，对数梯度图像的训练会导致更高的滤波器相似性，从而使CNN更加易于浮动。积极进取的一层量化，CNN资源降低和操作的综合益处无严格的暴露控制和图像信号处理（ISP）有助于将Tinyml CV推向其最终效率限制。
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.
