Our algorithm is characterized by two training stages. In the first stage we train FS, FT , AS, AT and both discriminators DS and DT . In addition, the discriminators are trained with the holistic images as input. In the second stage we interrupt the training of attention networks AS and AT and train the discriminators using the foregrounds only.
But in your code I didn't find out where it sets the training of discriminators using the foregrounds only. Could you point it out?
Thank you in advance.
When I read your paper, it says:
But in your code I didn't find out where it sets the training of discriminators using the foregrounds only. Could you point it out? Thank you in advance.