论文标题
低功率深度学习和计算机视觉的方法调查
A Survey of Methods for Low-Power Deep Learning and Computer Vision
论文作者
论文摘要
深度神经网络（DNN）在许多计算机视觉任务中都成功。但是，最准确的DNN需要数百万个参数和操作，使它们能量，计算和记忆密集型。这阻碍了在计算资源有限的低功率设备中大型DNN的部署。最近的研究通过减少记忆需求，能耗和操作数量来改善DNN模型，而不会显着降低准确性。本文调查了低功率深度学习和计算机视觉的进度，特别是在推理方面，并讨论了压实和加速DNN模型的方法。这些技术可以分为四个主要类别：（1）参数量化和修剪，（2）压缩卷积过滤器和矩阵分解，（3）网络体系结构搜索，以及（4）知识蒸馏。我们分析了每个类别中这些技术问题的准确性，优势，缺点和潜在解决方案。我们还讨论了新的评估指标，作为未来研究的指南。
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
