Generator forgetting in Generative Replay

Papers
1

Hi, just want to check with anyone who has implemented generative replay before if you have observed forgetting to happen when training the generator of the new Scholar. I implemented a DCGAN as my generator and I observed the generator to be only able to generate the latest set of samples.

I am not sure if I interpreted the paper wrongly. Is the generator of each new scholar supposed to be trained from scratch?

2

Dear @yedanqi, in this paper we explain all in detail.
I don’t recall the specs of the paper you mentioned but training incrementally the generator and the discriminator is known to be quite challenging.

@ggraffieti, the main author of the paper and an expert on Generative models trained continually, is your guy! :slight_smile: