MGGAN: Solving Mode Collapse Using Manifold-Guided Training

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.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yoshua Bengio,et al.  Better Mixing via Deep Representations , 2012, ICML.

[3]  Jacob Abernethy,et al.  On Convergence and Stability of GANs , 2018 .

[4]  Shakir Mohamed,et al.  Variational Approaches for Auto-Encoding Generative Adversarial Networks , 2017, ArXiv.

[5]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[6]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[7]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[8]  Andrew M. Dai,et al.  Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step , 2017, ICLR.

[9]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[10]  Hongyu Li,et al.  Similarity Measure for Vector Field Learning , 2006, ISNN.

[11]  Charles A. Sutton,et al.  VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning , 2017, NIPS.

[12]  David Pfau,et al.  Unrolled Generative Adversarial Networks , 2016, ICLR.

[13]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[14]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[16]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[17]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[18]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[19]  Yoshua Bengio,et al.  Mode Regularized Generative Adversarial Networks , 2016, ICLR.

[20]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[21]  Trung Le,et al.  Dual Discriminator Generative Adversarial Nets , 2017, NIPS.

[22]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[23]  Yoshua Bengio,et al.  Improving Generative Adversarial Networks with Denoising Feature Matching , 2016, ICLR.

[24]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[26]  Andrea Vedaldi,et al.  It Takes (Only) Two: Adversarial Generator-Encoder Networks , 2017, AAAI.

[27]  Andrea Vedaldi,et al.  Adversarial Generator-Encoder Networks , 2017, ArXiv.

[28]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[29]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[30]  David Berthelot,et al.  BEGAN: Boundary Equilibrium Generative Adversarial Networks , 2017, ArXiv.