Zhangjie Cao

We use a trick to reverse the gradient before the gradient back-propagate from discriminator to the feature extractor. So we do not need to use -1 at the discriminator loss...

Yes

Code for conditional adversarial domain adaptation will be published soon.

Yes, you can. But add more annotated data is usually better than using unsupervised target domain with domain adaptation. But if you use domain adaptation, you only need to annotate...

Maybe the caffe version we use is not compatible to your cudnn version. You can use the proper caffe version and copy our new developed codes to your own caffe.

You need to tune the parameters such as learning rate and the trade off for other base networks. You can also try to fix some layers of ResNet to prevent...

I mean try some hyper parameters such as learning rate and the trade off. And since ResNet os much more deeper than AlexNet, I suggest fixing the ResNet and only...

Why can't you get the dataset? Do you have access to the Google drive?

I think in the paper, the returned loss is weighted with w_ij, and it is calculated by Equation (2).

The loss is divided by |S| to average the loss since there are |S| pairs of codes.