中国计算机学会青年计算机科技论坛

CCF YOCSEF

于2016年11月2日（星期三）15:00-17:00，在南开大学津南校区计控学院419教室

深度学习的理论与应用论坛

14:45    签到

15:00    报告会开始

特邀讲者：屠卓文  副教授，加州大学圣地亚哥分校，计算机视觉最高奖Marr奖得主

报告题目：Deep supervision for deep learning: training, regularization, and multi-scale learning

特邀讲者：吴飞  教授，浙江大学，国家杰出青年基金获得者

报告题目：跨媒体群智深度计算

执行主席：程明明  博士，副教授，南开大学

屠卓文教授简介：

Prof. Zhuowen Tu is an associate professor in the Department of Cognitive Science and also affiliated with the Department of Computer Science and Engineering, at University of California, San Diego (UCSD). His research interests include computer vision, machine learning, deep learning, and neural computation.

吴飞教授简介：

吴飞，教授，博士生导师。主要研究领域为人工智能、跨媒体计算、多媒体分析与检索和统计学习理论。浙江大学计算机学院副院长、浙江大学人工智能研究所所长。国家杰出青年科学基金获得者（2016年）、教育部新世纪优秀人才支持计划入选者（2011年度）。于2009年10月至2010年8月在美国科学院院士、数理统计学会 (IMS) 前任主席、美国加州大学伯克利分校统计系前任系主任郁彬(Bin Yu)教授课题组做访问学者。主持国家自然科学基金-浙江两化融合联合基金重点项目1项、973课题1项、科技支撑计划课题1项、国家自然科学基金2项。目前担任SCI期刊Multimedia System副编审(Associate Editor)、SCI期刊Frontiers of Information Technology & Electronic Engineering (中国工程院子刊) 编委会成员、中国图象图形学会计算机动画与数字娱乐专委会副主任兼秘书长、中国计算机学会多媒体技术专业委员会常务委员、中国图象图形学学会第七届理事会理事。

屠卓文教授报告简介：

In this talk, the motivation and the benefits introducing of deep supervision to deep learning, convolutional neural networks in particular, will be discussed. We will then focus on our recent work, holistically-nested edge detection algorithm (HED) that tackles two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. HED performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets and it automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to resolve the challenging ambiguity in edge and object boundary detection. We significantly advance the state-of-the-art on the general edge/boundary detection task to reach human-level performance in the first time in the literature (to the best of our knowledge).

In addition, we will present a pooling strategy that generalizes existing pooling functions in convolutional neural networks. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in (1) learning a pooling function via (two strategies of) combining of max and average pooling, and (2) learning a pooling function in the form of a tree-structured fusion of pooling filters that are themselves learned. In our experiments every generalized pooling operation we explore improves performance when used in place of average or max pooling. We experimentally demonstrate that the proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets; they are also easy to implement, and can be applied within various deep neural network architectures. These benefits come with only a light increase in computational overhead during training and a very modest increase in the number of model parameters.

吴飞教授报告简介：

在现实世界中，不断涌现众包数据（如搜索引擎点击数据、Q-A问答数据等）中蕴含着丰富群智，反映着个体/群体间协作、竞争和激励等内隐意识。对时序众包数据的处理可看成序列数据深度学习过程。本报告将介绍序列数据深度学习基本方法和模型，以及我们将其应用于互联网图文搜索、Q-A问答和视觉文本生成等方面的工作，同时也将介绍这一方面研究所面临的挑战和未来发展趋势。