the numbers reported in the Siamese Net [11] paper

[ozabluda]

You say

I also can't find the numbers reported here in the Siamese Net [11] paper. As far as I can tell in their Table 2 they report one-shot accuracy, 20-way classification to be 92.0, while here it is listed as 88.1%?

They say:

For vision problems, we considered [...] our reimplementation of the Convolutional Siamese Net [11].

the re-implementation and/or training must be different, for example, [11] uses 400 classes, while "Matching Networks" uses 1600 classes (4x rotations).