News for hackers. Stuff that matters.
Re:Deep Neural Decision Forests [pdf] by strebler on Saturday November 14, 2015 @08:17PM (#10568088)
Why do they only compare their method against GoogLeNet? VGG was the winner in 2014, most papers seem to use VGG and my team has observed it to always gets higher accuracy than GoogLeNet.
Re:Deep Neural Decision Forests [pdf] by nl on Saturday November 14, 2015 @10:16PM (#10568339)
GoogLeNet "won" ImageNet 2014[1], but VGG is often found to be more flexible.

I'm not entirely sure, but I think that the multiple softmax layers in GoogLeNet might make it easier to modify for this purpose than the VGG architecture.

[1] http://image-net.org/challenges/LSVRC/2014/results (look for "Classification+localization with provided training data: Ordered by classification error")

Re:Deep Neural Decision Forests [pdf] by strebler on Saturday November 14, 2015 @11:38PM (#10568517)
Oh that's right, GoogLeNet did edge out VGG in the pure classification task. Localization is essential to us, so VGG was the clear winner for us :)