[HN Gopher] What Inception Net Doesn't See
___________________________________________________________________
What Inception Net Doesn't See
Author : Aliabid94
Score : 26 points
Date : 2021-02-15 20:01 UTC (1 days ago)
(HTM) web link (abidlabs.github.io)
(TXT) w3m dump (abidlabs.github.io)
| keyle wrote:
| SARAH CONNOR? <Sarah Connor does a handstand>
| Imnimo wrote:
| The ImageNet-A dataset (https://github.com/hendrycks/natural-adv-
| examples) contains thousands of hand-curated examples that are
| challenging for off-the-shelf classifiers. It's interesting to
| look through them and guess why each one's so difficult.
|
| For examples like the surgical mask, the ImageNet "mask" category
| is for masquerade masks and halloween masks, I suspect it doesn't
| contain anything similar to a surgical mask. Imagenet categories
| are a bit weird that way - they're a pretty arbitrary set of
| labels that were selected for use as a benchmark, not for
| practical use. It's got 100 different breeds of dogs, because it
| was a way to test fine-grained classification. It's got crane
| (the bird) and crane (the machine). It's got 'car mirror' but not
| 'mirror'. It's got 'yurt' but not 'house'.
|
| It's great if the categories you care about happen to match the
| ones on the list (in both name and type, as seen in the 'mask'
| example). But otherwise you'll quickly run into the need to fine-
| tune the model on some of your own data to get the categories you
| want.
| prashp wrote:
| This seems like a thinly veiled advertisement for Gradio. This is
| an otherwise trivial observation of convolutional neural
| networks, given the rapid pace of the field in general
| pool1892 wrote:
| how is this a new observation in any way?
| glsdfgkjsklfj wrote:
| I do not think it is supposed to be new. Everyone knows the
| flaws but downplay it _by a lot_. (negative proofs doesn 't get
| funding and all that...)
|
| I see this as a very funny way to recall what we always knew.
| Like a court jester reminding the king he was always naked.
| dwiel wrote:
| This analysis is quite the strawman. It's a bit like taking a
| demo SQL table and basic select queries off an intro to SQL
| tutorial and claiming SQL sucks because the queries are
| inefficient and the tables can only store books and author
| names but not any other kind of data because that's what the
| example was. There is a lot more to SQL than what gets
| introduced in the intro to SQL tutorial and there is a lot
| more to computer vision nets than grabbing the network
| trained on a benchmark dataset and shoving completely
| different data at it.
| sgt101 wrote:
| >there is a lot more to computer vision nets than grabbing
| the network trained on a benchmark dataset and shoving
| completely different data at it.
|
| Sure, you are right, but lots of people are wandering about
| saying different!
___________________________________________________________________
(page generated 2021-02-16 23:00 UTC)