Home > Seminars > Terrance Boult - The Deep Unknown

Terrance Boult - The Deep Unknown

Start:

9/27/2018 at 3:30PM

End:

9/27/2018 at 4:45PM

Location:

138 DeBartolo

Host:

College of Engineering close button
headerbottom

Walter Scheirer

Walter Scheirer

VIEW FULL PROFILE Email: walter.scheirer@nd.edu
Phone: 574-631-2436
Website: http://www.nd.edu/~wscheire
Office: 321C Stinson-Remick Hall

Affiliations

College of Engineering Assistant Professor
Primary interests in Computer Vision, Machine Learning, Biometrics,and Digital Humanities. Specific areas of research include Open Set Recognition, Extreme Value Theory Models for Visual Recognition, Biologically-inspired Learning Algorithms, and Stylometry.
Click for more information about Walter
574-631-2436
Add to calendar:
iCal vCal

The first part of the talk will explore issues with  deep networks dealing with  "unknowns" inputs, and the general issues of open set recognition in deep networks.  We review our first attempt at open set deep networks,  "OpenMax," and discuss is successes and limitations and why classic "open-set" approaches don't really solve the problem of deep unknowns.  We then present our ongoing work, to first appear at NIPS2018, on a new model we call the ObjectoSphere.  Using ObjectoSphere loss begins to address the learning of deep features that can handle unknown inputs.  We present examples of its use first on simple datasets sets (MNIST/CFAR) and then on a real-world problem of open-set face recognition.  

We then move to another type of unknown for deep networks:  adversarial examples, images  perturbations that are invisible to humans but easily fool deep networks.  While open set recognition tries to deal with inputs that are "far" from known training samples, these adversarial examples are in perceptually close in input space but far in feature face.  This last part of the talk will discuss various potential theories about the causes of adversarial examples,  why we know those theories are not correct, and why they show we don't understand deep networks.  We introduce our deep-feature adversarial approach, called LOTS, and return to the examples of object-recognition and face-recognition showing how our LOTS adversarial examples can successfully attack even open-set recognition systems.

Seminar Speaker:

Terrance Boult

Terrance Boult

University of Colorado

Bio forthcoming.