Events test

Filip Naiser presents High-frequency Component Helps Explain the Generalization of Convolutional Neural Networks

On 2020-10-13 11:00 at https://meet.google.com/icp-gxgd-bcb
Online reading group on "High-frequency Component Helps Explain the
Generalization of Convolutional Neural Networks"

Video conference link: https://meet.google.com/icp-gxgd-bcb
Instructions: http://cmp.felk.cvut.cz/~toliageo/rg/index2.html

Paper abstract: We investigate the relationship between the frequency spectrum
of image data and the generalization behavior of convolutional neural networks
(CNN). We first notice CNN’s ability in capturing the high-frequency
components of images. These high-frequency components are almost imperceptible
to a human. Thus the observation leads to multiple hypotheses that are related
to the generalization behaviors of CNN, including a potential explanation for
adversarial examples, a discussion of CNN’s trade-off between robustness and
accuracy, and some evidence in understanding training heuristics.

Material for the reading group:
https://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_High-Frequency_Component_Helps_Explain_the_Generalization_of_Convolutional_Neural_Networks_CVPR_2020_paper.pdf

Instructions for participants: The reading group studies the literature in the
field of pattern recognition and computer vision. At each meeting one or more
papers are prepared for presentation by a single person, the presenter. The
meetings are open to anyone, disregarding their background. It is assumed that
everyone attending the reading group has, at least briefly, read the paper –
not necessarily understanding everything. Attendants should preferably send
questions about the unclear parts to the speaker at least one day in advance.
During the presentation we aim to have a fruitful discussion, a critical
analysis of the paper, as well as brainstorming for creative extensions.

See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html

Za obsah zodpovídá: Petr Pošík