【IJAC推文】颜水成团队解读“高智商”机器人的终极杀器——深度学习

本文关键词

 

颜水成

360首席科学家

深度学习

（研究综述）

一直以来，棋类游戏都被视为顶级人类智力的试金石。1997年，国际象棋机器人第一次打败人类顶尖高手；9年后，人类最后一次打败国际象棋机器人。

围棋，因其需要计算的变化数量远远超过宇宙中已观测到的原子数量，令一众企图借蛮力穷尽算法的研究者们望而却步。然好景不长，继去年阿法狗大败九段手李世石后，人机大战2.0版也将于今年5月在乌镇正式开打。而支撑“高智商”机器人征战南北的终极杀器，正是火遍全球的“深度学习”技术。

 

说起“深度学习”，不禁联想到各大互联网公司、智商完美碾压小编的首席科学家们，其中当然少不了AI界大神、360首席科学家、人工智能研究院院长颜水成。

“

“深度学习”技术的本质就在于特征分层不依赖于研究者的设计，而是机器借助数据，像人脑一样主动学习的过程。“深度学习”有大量不同的架构方法，其中就包括基于卷积神经网络的架构方法和基于递归神经网络的架构方法。

”本期，小编隆重推荐由颜水成团队带来的关于“深度学习”的研究综述。他们回顾了基于“深度学习”的4种细粒度图像分类方法，以及基于“深度学习”的语义分割方法。如何让机器学会“认识”各种各样的鸟？如何让机器能够“看图说话”？答案就在文中~

A Survey on Deep Learning-based Fine-grained Object Classification and Semantic Segmentation

1收录信息：

Bo Zhao, Jiashi Feng, Xiao Wu, Shuicheng Yan. A Survey on Deep Learning-based Fine-grained Object Classification and Semantic Segmentation[J]. International Journal of Automation and Computing , vol. 14, no. 2, pp. 119-135, 2017.

2全文链接：

1）Springer Link:

https://link.springer.com/article/10.1007/s11633-017-1053-3

2）IJAC官网：

http://www.ijac.net/EN/abstract/abstract1901.shtml

3摘要：

The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks (CNNs), part detection based, ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.

4关键词：

Deep learning，fine-grained image classification，semantic segmentation，convolutional neural network (CNN)，recurrent neural network (RNN).

5作者简介：

1）Bo Zhao received the B. Sc. degree in networking engineering from Southwest Jiaotong University in 2010. He is a Ph.D. degree candidate at School of Information Science and Technology, Southwest Jiaotong University, China. Currently, he is at the Department of Electrical and Computer Engineering, National University of Singapore, Singapore as a visiting scholar.

His research interests include multimedia, computer vision and machine learning.

E-mail: [e-mail]

ORCID iD: 0000-0002-2120-2571

2）Jiashi Feng received the B.Eng. degree from University of Science and Technology, China in 2007, and the Ph.D. degree from National University of Singapore, Singapore in 2014. He was a postdoc researcher at University of California, USA from 2014 to 2015. He is currently an assistant professor at Department of Electrical and Computer Engineering, National University of Singapore, Singapore.

His research interests include machine learning and computer vision techniques for large-scale data analysis. Specifically, he has done work in object recognition, deep learning, machine learning, high-dimensional statistics and big data analysis.

E-mail: [e-mail]

3）Xiao Wu received the B.Eng. and M. Sc. degrees in computer science from Yunnan University, China in 1999 and 2002, respectively, and the Ph.D. degree in computer science from City University of Hong Kong, China in 2008. He is an associate professor at Southwest Jiaotong University, China. He is the assistant dean of School of Information Science and Technology, and the head of Department of Computer Science and Technology. Currently, he is at School of Information and Computer Science, University of California, USA as a visiting associate professor. He was a research assistant and a senior research associate at the City University of Hong Kong, China from 2003 to 2004, and 2007 to 2009, respectively. From 2006 to 2007, he was with the School of Computer Science, Carnegie Mellon University, USA as a visiting scholar. He was with the Institute of Software, Chinese Academy of Sciences, China, from 2001 to 2002. He received the second prize of Natural Science Award of the Ministry of Education, China in 2015.

His research interests include multimedia information retrieval, image/video computing and data mining.

E-mail: [e-mail] (Corresponding author)

ORCID iD: 0000-0002-8322-8558

4）Shuicheng Yan is currently an associate professor at the Department of Electrical and Computer Engineering, National University of Singapore, Singapore, the founding lead of the Learning and Vision Research Group (http://www.lvnus.org). He has authored/co-authored nearly 400 technical papers over a wide range of research topics, with Google Scholar citation>12 000 times. He is ISI highly-cited researcher 2014, and IAPR Fellow 2014. He has been serving as an associate editor of IEEE Transactions on Knowledge and Data Engineering, Computer Vision and Image Understanding and IEEE Transactions on Circuits and Systems for Video Technology. He received the Best Paper Awards from ACM MM’13 (Best paper and Best student paper), ACM MM’12 (Best demo), PCM’11, ACM MM’10, ICME’10 and ICIMCS’09, the runnerup prize of ILSVRC’13, the winner prizes of the classification task in PASCAL VOC 2010–2012, the winner prize of the segmentation task in PASCAL VOC 2012, the honorable mention prize of the detection task in PASCAL VOC’10, 2010 TCSVT Best Associate Editor (BAE) Award, 2010 Young Faculty Research Award, 2011 Singapore Young Scientist Award, and 2012 NUS Young Researcher Award.

His research interests include machine learning, computer vision and multimedia.

E-mail: [e-mail]

免责声明：文章部分内容借鉴自网络，版权归原作者所有。但因缺少作者详细信息，或无法确认真正原始作者，故未做详细标注，如涉及版权问题，请与IJAC编辑部联系，我们将第一时间协商版权问题或删除相关内容！

相关热文推荐：

【IJAC推文】周志华、吴建鑫等关于循环神经网络的最新研究成果

【IJAC热文】MIT Tomaso Poggio教授探讨深度学习机理

IJAC

International Journal of Automation and Computing

IJAC的出版服务不会止于论文发表。在论文发表后，IJAC也在积极地通过多种方式帮助作者提升研究成果的影响力，“IJAC推文”是其中一种方式，即通过互联网，以研究简介、实验视频等内容和形式，来帮助作者推广出版作品。

IJAC官方微信平台带您开启一场不一样的学术之旅，这里有最新会议资讯、研究成果、科普常识、美图美文，还有热情活泼而又不失严肃认真的阳光小编！

更多精彩内容，敬请关注：

IJAC官方网站：

1) http://link.springer.com/journal/11633

2) http://www.ijac.net 

微信公众号：IJAC

新浪微博：IJAC-国际自动化与计算杂志

Twitter: IJAC_Journal

Linked in(领英): 

Int. J. of Automation and Computing

本文编辑：欧梨成

长按识别二维码关注

点击阅读原文，免费下载全文