microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination
This addresses mode collapse in GANs for generative modeling, but it is incremental as it builds on existing multi-discriminator approaches.
The paper tackles the mode collapse problem in GANs by using multiple discriminators with microbatch assignments and a diversity parameter, resulting in early promotion of sample diversity across multiple datasets.
We propose to tackle the mode collapse problem in generative adversarial networks (GANs) by using multiple discriminators and assigning a different portion of each minibatch, called microbatch, to each discriminator. We gradually change each discriminator's task from distinguishing between real and fake samples to discriminating samples coming from inside or outside its assigned microbatch by using a diversity parameter $α$. The generator is then forced to promote variety in each minibatch to make the microbatch discrimination harder to achieve by each discriminator. Thus, all models in our framework benefit from having variety in the generated set to reduce their respective losses. We show evidence that our solution promotes sample diversity since early training stages on multiple datasets.