11–20 of 43 posts
It seems like, to be really good the AI needs to construct an internal 3D model of objects so it won't matter which way it's rotated. It seems to be how the human works. I can rotate an object in my mind and picture it from any angle.
It seems like, to be really good the AI needs to construct an internal 3D model of objects so it won't matter which way it's rotated. It seems to be how the human works. I can rotate an object in my mind and picture it from any angle.
You can, but I don't think that's what happens when looking at stuff. When I look at the hammer, I don't rotate a hammer to see what orientation matches what I'm seeing, I see the handle and... metal bit (don't know the term, sorry), realize those look like they belong to a hammer and go "oh yeah, it's an upside down hammer".
For me, I actually imagine these objects moving/rotating to make sense of them when seen from unusual angles. That hammer you described, I look at it and imagine myself flexing it.
I bet if you gave a human a short amount of time to identify these images, they'd have some mistakes too. Particularly the middle top one on the article
I bet if you gave a human a short amount of time to identify these images, they'd have some mistakes too. Particularly the middle top one on the article
I bet if you gave a human a short amount of time to identify these images, they'd have some mistakes too. Particularly the middle top one on the article
... it's a chair. Wow that took a minute. Some of these are devilishly tricky; clearly they're designed to hit all the difficult edge cases within the domain. What a fun dataset!
I bet if you gave a human a short amount of time to identify these images, they'd have some mistakes too. Particularly the middle top one on the article
But human can take more time and get it correct. Computers cannot simply take more time and be more accurate (I guess AlphaZero can, but that is a different problem entirely).
It would be nice at least if the computer tools could detect that they are confused, and I know there is some research in that direction.
My guess is every "hammer" image in the training data set was "conventional" -- a convenient angle and orientation. If half the images of "hammers" were instead "unconventional", would the model adapt to realize "my existing model of a hammer is incomplete; there must be a way to consolidate these two different images"?
Or does this require an internal 3d modeling, and better inputs wouldn't help; instead the model itself would need to be more advanced?
Being able to measure our successes and failures is the first step towards better algorithms :) This is always exciting. I don't think anyone thought that vanilla CNN architectures were all that would ever be needed. This paper which received an honorable mention this year from NeurIPS conference first attempts to convert the image to a 3d scene before detecting objects. https://arxiv.org/pdf/1906.01618.pdf
So, "construct an internal 3D model of [something in the natural world]" will always be deficient, and any conclusions derived from these models will always have inherent errors (even before you get to algo bias). Self-driving cars, airport face-reading gates, Pixar blockbusters...their models can never represent reality in anything but a temporarily-convincing way. Those that affect policy and peoples' lives (aka not-entertainment) will always come up with the wrong conclusion sometimes, sometimes fatally.