[HN Gopher] Seeing faces in things: A model and dataset for pare...
___________________________________________________________________
Seeing faces in things: A model and dataset for pareidolia
Author : sebg
Score : 31 points
Date : 2024-10-22 10:45 UTC (1 days ago)
(HTM) web link (mhamilton.net)
(TXT) w3m dump (mhamilton.net)
| aferr wrote:
| Can someone fine-tune this to find the face of Jesus in things?
| thih9 wrote:
| They have a method for finding animal doppelgangers, perhaps
| same approach could work on human faces. There is a demo next
| to the paragraph about it, quoted below.
|
| > We can even use the deep feature representation of our
| trained animal and pareidolia detector to compute animal-
| pareidolia doppelgangers
| Lerc wrote:
| Is there much in the way of datasets of things that are
| recognizable but triggering incorrect something-or-other (what is
| it exactly? Semantic sensations?)
|
| When we as humans see a face in a cookie or something we quite
| often spend some time gazing at it noting what it is about the
| the arrangement of features that triggers the pareidolia. I have
| wondered if that urge to contemplate the similarity difference is
| an instinctive response to gather more data for future accuracy.
|
| I guess in a similar vein there would be merit in collecting a
| data set of all of those quirks that generative AI produces to
| provide a point of comparison. Notably when most image generators
| produce artifacts it's because the local image generation is
| accurate but at odds with the global image. So fingers are beside
| fingers accurately but there are too many, or a swirl near some
| hair becomes hair but doesn't actually connect to the top of the
| head.
| bossyTeacher wrote:
| You are looking at it from your own rationalist point of view.
| Most humans will apply supernatural, magical, religious or/and
| spiritual meanings to it. This applies to faces in surfaces as
| well voices in wind or patterns in noise.
| gwern wrote:
| > Is there much in the way of datasets of things that are
| recognizable but triggering incorrect something-or-other (what
| is it exactly? Semantic sensations?)
|
| There are some datasets which collect 'hard' examples. One I
| love for the title alone is "When does dough become a bagel?
| Analyzing the remaining mistakes on ImageNet"
| https://arxiv.org/abs/2205.04596#google , Vasudevan et al 2022.
| The errors can be pretty interesting:
| https://arxiv.org/pdf/2205.04596#page=18 You can often see why
| a model might make a mistake and that you would too. (Like that
| first one of a swing - I would think it's some sort of large
| "tripod" too because I have no idea if I've ever seen a swing
| like _that_.)
___________________________________________________________________
(page generated 2024-10-23 23:00 UTC)