arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.09282cs.LGcs.CV
收藏

深度神经网络的模型压缩与加速研究综述

A Survey of Model Compression and Acceleration for Deep Neural Networks

Microsoft(微软);Tsinghua University(清华大学);Huazhong University of Science and Technology(华中科技大学)

Yu Cheng, Duo Wang, Pan Zhou, Tao Zhang

摘要:

深度神经网络(DNN)最近在许多视觉识别任务中取得了巨大成功。然而,现有的深度神经网络模型在计算上是昂贵的并且是存储密集的,这阻碍了它们在具有低存储器资源的设备中或者在具有严格延迟要求的应用中的部署。因此,一个自然的想法是在深度网络中执行模型压缩和加速,而不会显著降低模型性能。在过去五年中,这一领域取得了巨大进展。在本文中,我们回顾了最近用于压缩和加速DNN模型的技术。一般来说,这些技术分为四类:参数修剪和量化,低秩因式分解,转移/紧凑卷积滤波器,和知识蒸馏。首先介绍了参数修剪和量化的方法,然后介绍了其他技术。对于每个类别,我们还提供了有关性能,相关应用,优点和缺点的深入分析。然后介绍了一些最近比较成功的方法,如动态容量网络和随机深度网络。之后,我们调查了评估矩阵,用于评估模型性能的主要数据集,以及最近的基准测试工作。最后,对本文进行了总结,并讨论了存在的问题和未来的工作方向.

英文摘要:

Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past five years, tremendous progress has been made in this area. In this paper, we review the recent techniques for compacting and accelerating DNN models. In general, these techniques are divided into four categories: parameter pruning and quantization, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and quantization are described first, after that the other techniques are introduced. For each category, we also provide insightful analysis about the performance, related applications, advantages, and drawbacks. Then we go through some very recent successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrices, the main datasets used for evaluating the model performance, and recent benchmark efforts. Finally, we conclude this paper, discuss remaining the challenges and possible directions for future work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑