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 …
the ones in the right column aren’t rendered; they are real images, grossly misunderstood by deep learning