Adversarial Examples That Fool Both Computer Vision and Time-Limited Humans

Re:Adversarial Examples That Fool Both Computer Vision and T... by theoh on Monday November 12, 2018 @04:39PM (#18436119)

There are obviously classes of objects that we don't have hard-wired detectors for. The face is one of the few that I've heard claimed as wired from birth.

But I think "feature detectors" are exactly what the earlier comment was referring to, e.g. a Gabor-wavelet-style decomposition of the retinal image. Deep learning systems have to learn those; we're born with them.

[ Parent | on HN ]

Re:Adversarial Examples That Fool Both Computer Vision and T... by lisper on Monday November 12, 2018 @04:49PM (#18436202)

> Gabor-wavelet-style decomposition of the retinal image

Well, that's one theory. But I think it will turn out to be a lot more complex than that. One thing that I haven't seen anyone pay much attention to is feature detectors in the time domain, which we clearly have. We notice movement as a fundamental feature. Our movement detectors can actually be triggered by static images [1]. One of the ways we distinguish dogs from cats (I believe) is by the way they move. It would be a very interesting experiment to use CGI to make a dog move like a cat and vice versa and see how those are perceived.

[1] http://www.psy.ritsumei.ac.jp/~akitaoka/ICP2016.html

[ Parent | on HN ]