智能感知与计算系列讲座
Lecture Series in Intelligent Perception and Computing 

题    目（TITLE）：Deep supervision for deep learning: training, regularization, and multi-scale learning

讲 座 人（SPEAKER）: Associate Prof. Zhuowen Tu，University of California

主 持 人 (CHAIR)：Prof. Liang Wang

时    间 (TIME)：14:30 PM，July 7（Tuesday）, 2015

地    点 (VENUE)：The First Meeting Room,  3rd Floor，Intelligent Building

报告摘要（ABSTRACT）：
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 BSD500 dataset (ODS F-score of 0.782 and 0.797 respectively on the original and increased training data) and the NYU Depth dataset (ODS F-score of 0.746), and do so with an improved speed ($0.4$ second per image) that is orders of magnitude faster than some recent CNN-based edge detection algorithms.

报告人简介（BIOGRAPHY）：
Zhuowen Tu is an associate professor in the Department of Cognitive Science and also affiliated with the Department of Computer Science and Engineering, University of California, San Diego (UCSD). Before joining UCSD, he was a faculty member at UCLA. Between 2011 and 2013, he took a leave to work at Microsoft Research Asia. He received his Ph.D. from the Ohio State University and his M.E. from Tsinghua University. http://pages.ucsd.edu/~ztu/