View everything happening in ECE. Anyone with a campus netid can submit a calendar item.

ECE Distinguished Colloquium Series (ECE 500): "Cascaded Gain Control Representations for Visual Images"

Originating Calendar ECE ILLINOIS Distinguished Colloquium Series
Speaker Eero Simoncelli, NYU
Date: 2/1/2018
Time: 4 p.m.

Grainger Auditorium, Room 1002 ECE Building



Event Type: Seminar/Symposium

I’ll describe some recent work on developing models for visual representation based on a cascaded architecture, in which each stage performs convolutions with a set of kernels, an optional nonlinear rectification, and local gain control.  The first two operations are now commonly found in deep convolutional network architectures, but the third is generally not.  All three operations are primarily motivated by known functional properties of neural response throughout the visual system, and their parameters can be set by fitting physiological or perceptual data.  Alternatively, they can be optimized to capture statistical relationships found in natural images, or to achieve a specific engineering goal, such as restoration, compression, or recognition.

I’ll show examples of their use in quantifying perceptual distortion, optimizing the display of photographs (for example, rendering of high-dynamic range images), and as the basis of a new image compression system that is end-to-end optimized for its rate-distortion performance.

Eero Simoncelli received a BA in Physics from Harvard (1984), a Certificate of Advanced study in Math(s) from University of Cambridge (1986), and a MS and PhD in Electrical Engineering and Computer Science from MIT (1988/1993).  He was an assistant professor in the Computer and Information Science Department at the University of Pennsylvania from 1993 to 1996, and then moved to NYU as an assistant professor of Neural Science and Mathematics (later adding Psychology, and most recently, Data Science).  Eero received an NSF CAREER award in 1996, an Alfred P. Sloan Research Fellowship in 1998, and became an Investigator of the Howard Hughes Medical Institute in 2000.  He was elected a Fellow of the IEEE in 2008, and an associate member of the Canadian institute for Advanced Research in 2010.  He has received two Outstanding Faculty awards from the NYU GSAS Graduate Student Council (2003/2011), two IEEE Best Journal Article awards (2009/2010) and a Sustained Impact Paper award (2016), an Emmy Award from the Academy of Television Arts and Sciences for a method of measuring the perceptual quality of images (2015), and the Golden Brain Award from the Minerva Foundation, for fundamental contributions to visual neuroscience (2017).

His group studies the representation and analysis of visual images in biological and machine systems.

To request disability-related accommodations for this event, please contact the person listed above, or the unit hosting the event.