Possible reasons for similarity among generated images about dcgan.torch

[soumith]

are your second set of generations on a pre-trained network?

[vasavig]

No, I had trained both the networks from scratch on Celeb dataset, with the only difference of how I created the input to generator, as I explained in my comment.

[vasavig]

Seems like this is a mode collapse problem where the generator is modeling the distribution to one Gaussian rather than a mixture of Gaussians. More pointers on the mode collapse problem can be found in Ian Goodfellow's 2016 NIPS tutorial, https://arxiv.org/abs/1701.00160.

[danieleghisi]

@vasavig Did you find a way to overcome this problem?

[danieleghisi]

In this paper the authors claim to have solved the mode collapse issue via "unrolling" the Adam objective.
I wouldn't be able to implement any of this in the current model, but it might be cool to consider it...?