61–70 of 114 posts
The net correctly identified "leopard". Was it taught about sofas? Who knows, maybe Sofa had a high score as well on the output.
Or, look at the Dalmatian/Cherry picture. The net identified "Dalmatian" which is a 100% valid response! But whoever labeled it wanted "cherry". The picture is 50% cherry 50% dalmatian.
Pictures often have more than one element and a pure ConvNet is "one picture to one label"
Yes, ConvNets are limited and results are pretty arbitrary sometimes. The net correctly identified "leopard". Was it taught about sofas? Who knows, maybe Sofa had a high score as well on the output. Or, look at the Dalmatian/Cherry picture. The net identified "Dalmatian" which is a 100% valid response! But whoever labeled it wanted "cherry". The picture is 50% cherry 50% dalmatian. Pictures often have more than one e…
This article would not come as a surprise to anyone who works with ConvNets. Sadly, that might not the case for those outside of the field, largely due to media's inadequate coverage of our advances (but this is common outside our field too). No one in the field really believes ConvNets see better than humans. They are very good single glance texture recognizers. It's as if you flashed an image and looked at it for a…
Next step is Video. Adding temporal dimension will emphasize extrapolating true 3d shapes of recognized objects.
Thank you for this article; very thought provoking. My nitpick: > When each student was given a heavy book of MNIST database, hundreds of pages filled with endless hand-written digit series, 60000 total, written in different styles, bold or italic, distinctly or sketchy. > ... > So, are you going to say that was not the case? I understand the point the author is making. Human brains are really good at taking limited…
Obviously these classifiers do often focus on patterns, rather than shapes, and that's probably something that could be worked on, but I don't think an image classifier can possibly be expected to, at the level it is operating, identify the leopard-print sofa all on its own. Clearly there's a higher order process at work than image recognition here - after all, when a human is faced with a sofa-shaped object with a l…
This, given the leopard couch, returns "brown leopard print couch".
https://www.imageidentify.com/ correctly identified the images as "a small sofa". I think rotating the image is questionable, since there could be an algorithm for first orienting the image correctly based on light and shadow and then the image recognition could be run. https://www.imageidentify.com/result/1ixb9603m9ix1
If part of the network is trained on the concept of a cat, and whether or not an image is a cat is fed into training of the leopard, it seems like the problems would be avoided. Or is the notion that with enough training data and deep enough networks the concept of "leopard is cat" will be learned?