Note that these are both approaches to do "fine-scaled visual categorization" (FGVC), which assumes you already know you're looking at a dog/bird and want to identify which species it is. This is increasingly becoming an important problem in computer vision, and in fact we just recently held the 2nd FGVC workshop [1] this year to encourage more people to work on these sorts of things.
The kaggle competition is for determining if it is a dog or cat, so it's a bit unlikely that one of these approaches would directly work (although they might be adaptable to the task). See my other comment [2] for a lighter-weight approach that is likely to do just as well, if not better.
The kaggle competition is for determining if it is a dog or cat, so it's a bit unlikely that one of these approaches would directly work (although they might be adaptable to the task). See my other comment [2] for a lighter-weight approach that is likely to do just as well, if not better.
[1] http://www.fgvc.org/
[2] https://news.ycombinator.com/item?id=6446309