pmorerio / admd

Tensorflow code for the paper 'Learning with privileged information via adversarial discriminative modality distillation', TPAMI 2019
MIT License
10 stars 3 forks source link

Feature for comparison ResNet-50 on NYU #10

Open Scienceseb opened 4 years ago

Scienceseb commented 4 years ago

I just want to check that I use the right features to train the hallucination network, I use the feature map coming out of the first FC layer of the sequential fully connected module (the output of (0) in the third image) . Is this equivalent to your Tensorflow code, according to your artcile it's the same thing.
See the following images:

The code: image image

The FC connected module: image