Hi all,

we have two tea-talks today. You can find the detail of the talks in my previous email.

Best,

--Junyoung

On Mon, May 29, 2017 at 6:58 PM Junyoung Chung <elecegg@gmail.com> wrote:

Hi all,

we have two tea-talks (each is a 30-min talk) this week!

Both speakers are from Univ. of Laval.

You will find more information below. 

Talk by Christian Gagné 

Time: 13:45~14:15

Title:

Alternating Direction Method of Multipliers for Sparse Convolutional Neural Networks

Abstract: 

The storage and computation requirements of Convolutional Neural Networks (CNNs) can be prohibitive for exploiting these models over low-power or embedded devices. We are proposing to reduce the computational complexity of the CNNs by minimizing an objective function, including the recognition loss that is augmented with a sparsity-promoting penalty term. The sparsity structure of the network is identified using the Alternating Direction Method of Multipliers (ADMM), which is widely used in large optimization problems. This method alternates between promoting the sparsity of the network and optimizing the recognition performance, which allows us to exploit the two-part structure of the corresponding objective functions. In particular, we take advantage of the separability of the sparsity-inducing penalty functions to decompose the minimization problem into sub-problems that can be solved sequentially. Applying our method to a variety of state-of-the-art CNN models, our proposed method is able to simplify the original model, generating models with less computation and fewer parameters, while maintaining and often improving generalization performance. Accomplishments on a variety of models strongly verify that our proposed ADMM-based method can be a very useful tool for simplifying and improving deep CNNs.

Short bio:

Christian Gagné is professor at the Electrical Engineering and Computer Engineering Department of Université Laval since 2008. He is member of the Computer Vision and Systems Laboratory, the REPARTI FRQNT Strategic Cluster, and the Big Data Research Centre. He completed a Ph.D. in Electrical Engineering (Université Laval) in 2005 before being postdoctoral fellow at the INRIA Saclay - Île-de-France (France) and the University of Lausanne (Switzerland) in 2005-2006. He was research associate for Informatique WGZ Inc. (2006-2007) and MacDonald, Dettwiler, and Associates Ltd. (2007-2008). His research interests are on the engineering of intelligent systems, especially systems based on machine learning, evolutionary computing, and their application to pattern recognition, smart sensors, smart grids, and simulation of public health processes.

Talk by Jean-François Lalonde 

Time: 14:15~14:45

Title: 

Learning to Predict Illumination from a Single Image

Abstract: 

We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of a scene. In contrast to previous work that relies on specialized image capture, user input, and/or simple scene models, we train an end-to-end deep neural network that directly regresses a limited field-of-view photo to HDR illumination, without strong assumptions on scene geometry, material properties, or lighting. This allows us to automatically recover high-quality HDR illumination estimates that significantly outperform previous state-of-the-art methods. Consequently, using our illumination estimates for applications like 3D object insertion, we can achieve results that are photo-realistic.

Bio:

Jean-François Lalonde is an Assistant Professor in Electrical and Computer Engineering at Laval University, Quebec City, since 2013. Previously, he was a Post-Doctoral Associate at Disney Research, Pittsburgh. He received a B.Eng. degree in Computer Engineering with honors from Laval University, Canada, in 2004. He earned his M.S at the Robotics Institute at Carnegie Mellon University in 2006 under Prof. Martial Hebert and received his Ph.D., also from Carnegie Mellon, in 2011 under the supervision of Profs. Alexei A. Efros and Srinivasa G. Narasimhan. His thesis, titled "Understanding and Recreating Appearance under Natural Illumination," won the 2010-11 CMU School of Computer Science Distinguished Dissertation Award. After graduation, he became a Computer Vision Scientist at Tandent, Inc., where he helped develop LightBrush™, the first commercial intrinsic imaging application. He also introduced intrinsic videos at SIGGRAPH 2012 while at Tandent. His research focuses on lighting-aware image understanding and synthesis by leveraging large amounts of data. More at www.jflalonde.ca. 

Best,

--Junyoung

--

--Junyoung