Hierarchical Modes Exploring in Generative Adversarial Networks

Abstract

In conditional Generative Adversarial Networks (cGANs), when two different initial noises are concatenated with the same conditional information, the distance between their outputs is relatively smaller, which makes minor modes likely to collapse into large modes. To prevent this happen, we proposed a hierarchical mode exploring method to alleviate mode collapse in cGANs by introducing a diversity measurement into the objective function as the regularization term. We also introduced the Expected Ratios of Expansion (ERE) into the regularization term, by minimizing the sum of differences between the real change of distance and ERE, we can control the diversity of generated images w.r.t specific-level features. We validated the proposed algorithm on four conditional image synthesis tasks including categorical generation, paired and un-paired image translation and text-to-image generation. Both qualitative and quantitative results show that the proposed method is effective in alleviating the mode collapse problem in cGANs, and can control the diversity of output images w.r.t specific-level features.

References in corpus (9)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Toward Multimodal Image-to-Image Translation
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
• Stochastic Adversarial Video Prediction
• On GANs and GMMs
• JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets