[p1esk]

What do you mean they “kinda” work? NAS is all the rage these days. SOA on Imagenet [1], SOA for mobile [2]. Still needs a ton of gpus, but search algorithms getting smarter every month.

PS I have to admit, your papers made me laugh :)

[1] https://arxiv.org/abs/1811.06965

[2] http://www.arxiv-sanity.com/1807.11626v2

[dimatura]

Oh yeah, can't argue with results. Similar to deep learning. I've used both deep learning and metaheuristics a fair amount -- I don't care too much about mathematical rigor ;). I just mean, it's the sort of thing that usually needs experimentation, domain knowledge and maybe a bit of luck.

[hooloovoo_zoo]

I want to know what 1's CIFAR transfer results are w/o cutout.

[p1esk]

FYI, they compare their cifar results to [1], which is more effective than plain cutout.

[1] https://arxiv.org/abs/1805.09501

[hooloovoo_zoo]

Heh, I'm familiar with this one too. It implies that, for instance, the Shake-Shake and Shake-Drop papers employ cutout, which they don't report. It's hard to make apples to apples comparisons when they're changing lots of things at the same time.