Shared Loss between Generators of GANs
This addresses the mode collapse issue for researchers and practitioners using GANs, though it appears incremental as it builds on existing multiple generator frameworks.
The paper tackles the mode collapse problem in GANs by introducing a framework where multiple generators compete against each other while interacting with the discriminator, resulting in a dramatic reduction in training time without affecting performance.
Generative adversarial networks are generative models that are capable of replicating the implicit probability distribution of the input data with high accuracy. Traditionally, GANs consist of a Generator and a Discriminator which interact with each other to produce highly realistic artificial data. Traditional GANs fall prey to the mode collapse problem, which means that they are unable to generate the different variations of data present in the input dataset. Recently, multiple generators have been used to produce more realistic output by mitigating the mode collapse problem. We use this multiple generator framework. The novelty in this paper lies in making the generators compete against each other while interacting with the discriminator simultaneously. We show that this causes a dramatic reduction in the training time for GANs without affecting its performance.