VARGAN: Variance Enforcing Network Enhanced GAN
This addresses mode collapse in GANs for generative modeling, but it appears incremental as it builds on existing GAN frameworks with an added network component.
The paper tackles the problem of mode collapse and unstable training in GANs by introducing VARGAN, a new architecture that uses a third network to enforce diversity in generated samples, resulting in more diverse samples compared to state-of-the-art models on synthetic and real-world image data.
Generative adversarial networks (GANs) are one of the most widely used generative models. GANs can learn complex multi-modal distributions, and generate real-like samples. Despite the major success of GANs in generating synthetic data, they might suffer from unstable training process, and mode collapse. In this paper, we introduce a new GAN architecture called variance enforcing GAN (VARGAN), which incorporates a third network to introduce diversity in the generated samples. The third network measures the diversity of the generated samples, which is used to penalize the generator's loss for low diversity samples. The network is trained on the available training data and undesired distributions with limited modality. On a set of synthetic and real-world image data, VARGAN generates a more diverse set of samples compared to the recent state-of-the-art models. High diversity and low computational complexity, as well as fast convergence, make VARGAN a promising model to alleviate mode collapse.