News for hackers. Stuff that matters.
Re:Improving Deep Learning Performance with AutoAugment by tlb on Tuesday June 19, 2018 @08:01PM (#17351308)
An example they give is that it doesn't apply shear transforms to CIFAR-10, because there aren't sheared examples in the (test) data. That makes it less indicative of real-world vision performance, given that human vision is fairly robust to shear.

An opposite sort of strategy is to apply every augmentation that doesn't increase human error rate on a test sample.

Re:Improving Deep Learning Performance with AutoAugment by mlthoughts2018 on Tuesday June 19, 2018 @10:16PM (#17352034)
Sure, I think the approach could work successfully in some cases, but I think specifically allowing it to learn transformations of the input color space would be quite problematic — you are essentially giving it more degrees of surface statistics freedom with which to data mine a better looking overfitting metric during validation steps.