Neural networks basically just learn to classify textures.https://twitter.com/karpathy/status/1091813185995358208 …
-
They might, if they are allowed to. The fact that you can do this for me reflects more poorly on ImageNet than ConvNets
I wonder how well humans do? We're pretty good at recognizing closeups where most of an object is obscured.
-
-
Put another way, I wonder to what extent it's true that, to paraphrase
@pfau: "humans are basically just good at learning to classify local textures". -
To me that would be at odds with how effortless it is to eg watch cartoons, interpret art, etc. that said, I’ve seen a few examples where ConvNets also possess this ability but to a lower extent, I suspect because they are allowed to be lazy in their training data.
- 5 more replies
New conversation -
-
-
For humans, check out the human experiments section of https://arxiv.org/abs/1811.12231 :-) If you give a CNN a cat with elephant texture, it says "elephant", human says "cat"...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.