Loading Events

« All Events

  • This event has passed.

Spring 2018 GRASP Seminar Series: Michael Maire, Toyota Technological Institute, “Architecting and Regularizing Deep Convolutional Neural Networks”

January 12, 2018 @ 11:00 am - 12:00 pm

ABSTRACT

Deep convolutional neural networks (CNNs) are central to modern computer vision systems. This talk covers two recent works which explore new ideas in CNN architectures and training procedures.

The first proposes a multigrid extension of CNNs. Here, network layers operate across scale space, consuming multigrid inputs and producing multigrid outputs; convolutional filters themselves have both within-scale and cross-scale extent. Multigrid structure enables such networks to learn internal attention and dynamic routing mechanisms, and use them to accomplish tasks on which standard CNNs fail.

The second constructs custom regularization functions for use in supervised training of CNNs. This technique is applicable when the ground-truth labels themselves exhibit internal structure; it derives a regularizer by learning an autoencoder over the set of annotations. Training thereby becomes a two-phase procedure. The first phase models labels with an autoencoder. The second phase trains the actual network of interest by attaching an auxiliary branch that must predict output via a hidden layer of the autoencoder.

Joint works with Tsung-Wei Ke and Stella X. Yu, as well as Mohammadreza Mostajabi and Gregory Shakhnarovich.

Presenter

- Learn More

Michael Maire is a Research Assistant Professor at the Toyota Technological Institute at Chicago (TTIC). He received a B.S. with honors from the California Institute of Technology (Caltech) in 2003, and a Ph.D. in computer science from the University of California, Berkeley, in 2009. Prior to joining TTIC, he was a postdoctoral scholar in the Department of Electrical Engineering at Caltech. His research is centered around the development of algorithms for understanding visual scenes, with emphasis on the problems of object detection and segmentation.

Details

Date:
January 12, 2018
Time:
11:00 am - 12:00 pm
Event Category: