search

abhimanyudubey / confusion

Code for the ECCV 2018 paper "Pairwise Confusion for Fine-Grained Visual Classification"
https://arxiv.org/abs/1705.08016
200 stars 39 forks source link

Implementation issue for bilinear VGG #1

Closed aniket03 closed 7 years ago

aniket03 commented 7 years ago

In your implementation of bilinear VGG in caffe, I found out that num_output for bilinear_layer is at 8192. But I do not understand how is it so? Because no of output for this layer should be equal to 512x512 if we take outer product of the preceding layer output with itself.

aniket03 commented 7 years ago

I now understand this. You have used compact bilinear pooling also. If possible can you also pls share the link on implementation of "bilinear layers" in caffe.