Path-breaking Papers About Image Classification

Re:Path-breaking Papers About Image Classification by kushankpoddar on Wednesday August 16, 2017 @05:31AM (#15026110)

Sometimes I wonder why is the top-5 image classification task so difficult. If you are giving me 5 chances to look at an image and correctly classify it from ~1000 Imagenet classes, I can surely do better than 5-10% error rate.

Also, now that the top-5 error rate been brought down considerably, what is the next benchmark for the research community to beat? A new dataset, top-1 error rate on Imagenet?

[ Parent | on HN ]

Re:Path-breaking Papers About Image Classification by parths on Wednesday August 16, 2017 @06:08AM (#15026275)

A large majority of human errors come from fine-grained categories(such as correctly identifying two similar cat species) and class unawareness. I would recommend this article by Andrej Karpathy, where he talks about his learning from competing against GoogLeNet: http://karpathy.github.io/2014/09/02/what-i-learned-from-com...

[ Parent | on HN ]

Re:Path-breaking Papers About Image Classification by AstralStorm on Wednesday August 16, 2017 @01:30PM (#15029389)

That would be relatively low grade error. Specifically errors have to be valued and not just counted.

[ Parent | on HN ]