MGGAN: Solving Mode Collapse using Manifold Guided Training
arXiv:1804.04391
Abstract
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.
References in corpus (12)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Density estimation using Real NVP
- Adversarial Feature Learning
- Adversarially Learned Inference
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- Towards Principled Methods for Training Generative Adversarial Networks
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Mode Regularized Generative Adversarial Networks
- Better Mixing via Deep Representations
- Dual Discriminator Generative Adversarial Nets
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Cited by in corpus (10)
- A survey on GANs for computer vision: Recent research, analysis and taxonomy
- Review: Deep Learning in Electron Microscopy
- A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
- Compressing PDF sets using generative adversarial networks
- Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
- DualDis: Dual-Branch Disentangling with Adversarial Learning
- Future Frame Prediction of a Video Sequence
- Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
- Mode Penalty Generative Adversarial Network with adapted Auto-encoder
- SVMax: A Feature Embedding Regularizer