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

On 2020-10-13 - 2020-10-13 11:00:00 at
Online reading group on "High-frequency Component Helps Explain the
Generalization of Convolutional Neural Networks"

Video conference link:

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:

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

Za obsah zodpovídá: Petr Pošík