Presented By
O’REILLY + INTEL AI

English中文
PUT AI TO WORK
June 18-21, 2019
Beijing, CN

在边缘实现深度学习

此演讲使用中文 (This will be presented in Chinese)

陈玉荣 (Intel)
13:1013:50 Friday, June 21, 2019
模型与方法 (Models and Methods)
Location: 多功能厅6A+B (Function Room 6A+B)

必要预备知识 (Prerequisite Knowledge)

Deep learning basic knowledge, CNN architecture basic knowledge, DNN quantization and optimization basic knowledge.

您将学到什么 (What you'll learn)

Three key ways to enable deep learning inference at the edge devices from DNN algorithm design perspective

描述 (Description)

英特尔中国研究院认知计算实验室聚焦视觉认知(包含感知、识别、理解及认知)和机器学习的前沿技术研究,以此来实现英特尔智能计算的新颖应用及用户体验。过去三年,我们专注基于深度学习的视觉理解合成研究,大胆进行技术创新,同时也注重技术落地,取得了丰硕的研究成果。在计算机视觉,机器学习和深度学习领域,我们获得专利申请批准60余项,发表了近30篇CV/ML/AI顶级会议论文。同时,我们还向英特尔产品部门完成了13项技术转化,包括3项重大技术转化。这些技术转化影响了英特尔的软硬件平台设计,提升了英特尔产品的用户体验。此外,我们还在多项世界级的视觉识别和理解挑战赛中获得佳绩,并为多个英特尔品牌推广活动,包括李宇春人工智能音乐视频、长城自然遗产保护及保护野生动物东北虎,提供关键人工智能技术及相关技术支持。

深度学习在许多领域尤其是视觉识别/理解方面取得了巨大突破,但它在训练和部署方面都存在一些挑战。本讲座将着重介绍我们通过算法创新来解决深度学习部署挑战,在边缘实现深度学习的前沿研究工作。这些算法创新包括高效CNN算法设计、领先DNN模型压缩技术和部署时DNN网络结构优化技术等。

我们的高效CNN算法设计主要集中在物体检测任务上,因为它是视觉识别理解的最基本任务。我们设计了几种新颖的CNN网络结构来实现高效准确的物体检测,包括最先采用卷积层特征聚合技术来提高小目标物体检测准确度的HyperNet (CVPR’16),最早提出特征金字塔表示特征进行物体检测工作之一的RON (CVPR’17),最先提出从头开始训练的物体检测器DSOD (ICCV’17),以及在DSOD基础上提出的轻量级物体检测器Tiny-DSOD (BMVC’18)。其中,DSOD及Tiny-DSOD已被使用于英特尔Unite和Altia PanaCast Systems的智能视频会议系统。

除了具有针对性的高效网络结构设计外,DNN模型压缩是在边缘端实现深度学习推断的另一项关键技术。我们研究开发了一整套业界领先的不损失模型推断准确度的深度神经网络压缩技术,包括DNS (NIPS’16),Network Slimming (ICCV’17)等多种DNN网络剪枝技术,以及INQ (ICRL’17),Network Sketching (CVPR’17),MLQ (AAAI’18),ELQ (CVPR’18)等低比特DNN模型量化技术。尤其是我们最近提出的ELQ超低比特量化技术在ImageNet数据集上实现了三值和二值CNN模型量化的领先准确度。我们的这套技术已经获得十余项美国专利申请批准,并作为英特尔研究院的一项重大技术转化,帮助英特尔产品部门来提升英特尔平台的深度学习推断软硬件加速能力。

DNN模型压缩技术通常要进行重训练,来确保模型推断准确度(尽量)不损失。重训练是比较耗时的,并且在很多时候我们不能获得用户的数据进行重训练。为了解决这个问题,我们还提出了一套部署时DNN网络结构优化技术,包括网络解耦Network Decoupling (BMVC’18), 复合二值分解网络CBDNet (AAAI’19),少量知识蒸馏等,它的优点是不需要重训练及深度学习专家参与,就可以在部署DNN时,对其进行加速。

Photo of 陈玉荣

陈玉荣

Intel

Dr. Yurong Chen is a Principle Research Scientist and Sr. Research Director at Intel Corporation, and Director of Cognitive Computing Lab at Intel Labs China. Currently, he’s responsible for driving cutting-edge Visual Cognition and Machine Learning research for Intel smart computing. He is also the co-owner of Intel Labs “Visual Understanding and Synthesis” program, driving research innovation in smart visual data processing technologies on Intel platforms across Intel Labs. He drove the research and development of Deep Learning (DL) based Visual Understanding (VU) and leading Face Analysis technologies to impact Intel architectures/platforms and delivered core technologies to help differentiate Intel products including Intel RealSense SDK, CV SDK, IOT video E2E analytics solutions and client apps. He led the team to win Intel China Award (Top team award of Intel China) 2016, Intel Labs Academic Awards (Top award of Intel labs) – Gordy Award 2016, 2015 and 2014 for outstanding research achievements on DL based VU, Multimodal Emotion Recognition and Advanced Visual Analytics. Dr. Chen joined Intel in 2004 after finishing his postdoctoral research in the Institute of Software, CAS. He received his Ph.D. degree from Tsinghua University in 2002. He has published over 50 technical papers, and holds 10+ issued/pending US/PCT patents and 30+ patent applications.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)