MGGAN: Solving Mode Collapse using Manifold Guided Training
This addresses a critical problem in GAN training for researchers and practitioners, offering an incremental improvement that is easily extendable to existing GANs.
The paper tackles mode collapse in generative adversarial networks (GANs) by proposing MGGAN, a manifold guided training algorithm that uses a guidance network to help the generator learn all data distribution modes, resolving mode collapse without sacrificing image quality.
Mode collapse is a critical problem in training generative adversarial networks. To alleviate mode collapse, several recent studies introduce new objective functions, network architectures or alternative training schemes. However, their achievement is often the result of sacrificing the image quality. In this paper, we propose a new algorithm, namely a manifold guided generative adversarial network (MGGAN), which leverages a guidance network on existing GAN architecture to induce generator learning all modes of data distribution. Based on extensive evaluations, we show that our algorithm resolves mode collapse without losing image quality. In particular, we demonstrate that our algorithm is easily extendable to various existing GANs. Experimental analysis justifies that the proposed algorithm is an effective and efficient tool for training GANs.