Re:Improving Deep Learning Performance with AutoAugment
by nafizh on Tuesday June 19, 2018 @06:22PM
(#17350765)
Don't exactly remember the paper, but many of the claims in the paper you mentioned were seemed to be proven false. As such, augmentation like this should, if any, reduce overfitting.
[ Parent
| on HN ]
Re:Improving Deep Learning Performance with AutoAugment
by mlthoughts2018 on Tuesday June 19, 2018 @10:13PM
(#17352017)
Could you provide a link to where the Bengio paper was “disproven”?
I would be quite surprised to learn that, especially for the experimental result they have with the low-pass Fourier filter on the training set, and also because the Bengio paper is quite recent.
Re:Improving Deep Learning Performance with AutoAugment
by jjn2009 on Tuesday June 19, 2018 @07:13PM
(#17351047)
I agree, as long as you do out of sample testing correctly then using this as a benchmark for finding the correct transformations to perform should reduce overfitting.
That said I can see how if done incorrectly you could easily end up overfitting instead.