I love these examples too, but there's something funny to me about describing these results as "fooling" DL (as authors suggest). These images are...extremely weird. Why does DL need to call an impossibly diagonal, cropped, photoshopped vehicle a "firetruck" to impress us?https://twitter.com/GaryMarcus/status/1068169331832315906 …
Either I have misunderstood your tweet or you have not read the paper carefully
-
-
The former, I think. But maybe because I misunderstood your initial tweet? We should definitely be alarmed by DL's performance on column (d). Should we also be alarmed by DL's performance on columns (b) and (c)? The paper itself focuses much more on those, hence my tweet.
-
This isn't a hill I'll die on, but I've just noticed myself feeling like 100x more compelled by critiques like Fodor & Pylyshyn '88, your '98, etc., than by adversarial images and "fooling".
- 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.