No recording or live stream video available yet.

Please check back a few days before the event starts.

Towards Frequency-Based Explanation for Robust CNN

Time: Wednesday 15-Jul-2020 16:00
Live in 3 days & 02:33:20

Speaker:
Discussion Moderator:

Artifacts

Motivation / Abstract
Computer Vision implementations based on Convolutional Neural Networks (CNN) have been reported to be unstable and vulnerable to adversarial attacks that are not visible to humans.  The authors are presenting novel work to better identify algorithms that are vulnerable to these attacks and present explainable options to help design better models.
Questions Discussed
1) Is your method helping models ignore the noise in a similar way that human cognition filters out irrelevant information?
2) Why is adversarial training expensive?  How does your method improve on adversarial training?
3) Do you need access to the model to generate your explanations?
Stream Categories:
 ML Interpretability

Join This Event

Live chat will be available close to event start date.


View All Upcoming Events
Code of ConductTerms and Conditions