Home > Events > Oral Candidacy - Brandon RichardWebster

Oral Candidacy - Brandon RichardWebster

Start: 4/16/2019 at 7:00PM
End: 4/16/2019 at 9:00PM
Location: 315 Stinson Remick
Attendees: Faculty and students are welcome to attend the presentation portion of the defense.
Add to calendar:
iCal vCal

Brandon RichardWebster

Oral Candidacy Exam

April 16, 2019      7:00 pm      315 Stinson Remick

Adviser:  Dr. Walter Scheirer

Committee Members:

Dr. Adam Czajka      Dr. Patrick Flynn      Dr. Michael Milford

Title: 

"Visual Psychophysics For Computer Vision"

Abstract: 

By providing substantial amounts of data and standardized evaluation protocols, datasets in computer vision have helped fuel advances across all areas of visual recognition. But even in light of breakthrough results on recent benchmarks, it is still fair to ask if our recognition algorithms are doing as well as we think they are. The vision sciences at large make use of a very different evaluation regime known as Visual Psychophysics to study visual perception. Psychophysics is the quantitative examination of the relationships between controlled stimuli and the behavioral responses they elicit in experimental test subjects. Instead of using summary statistics to gauge performance, psychophysics directs us to construct item-response curves made up of individual stimulus responses to find perceptual thresholds, thus allowing one to identify the exact point at which a subject can no longer reliably recognize the stimulus class.

In this work I will demonstrate the efficacy of visual psychophysics for computer vision from four main perspectives: visual psychophysics for evaluation, visual psychophysics for explainability, visual psychophysics for improved generalizability, and finally visual psychophysics for a real life application. The arch from evaluation to application completes a life cycle of a computer vision algorithm, providing positive evidence to the community that visual psychophysics can aid any stage of development.