Re:Leaf: Machine learning framework in Rust
by YeGoblynQueenne on Tuesday March 08, 2016 @04:35PM
(#11248887)
> First of all no one ever expected machines to beat humans at Imagenet.
I'm not contesting the fact that it's surprising and overall a sign of progress. I'm contesting the claim that it demonstrates "superhuman" performance.
By analogy, a good student at a bad school is "superhuman" because he or she got a good mark in an exam that most other pupils _in that school_ failed. You gotta go a lot further than that before you put on the red cape.
Second the examples were produced by scraping Flickr. Then mechanical turkers were asked to confirm if the object was in the image or not.
There are many images that are kind of ambigious, or contain multiple objects, so humans don't do perfectly. One researcher tried to estimate human performance, and got about 5%. Which has been beaten by computers now, by a lot.