MMGAN: Manifold Matching Generative Adversarial Network

It is well-known that GANs are difficult to train, and several different techniques have been proposed in order to stabilize their training. In this paper, we propose a novel training method called manifold-matching, and a new GAN model called manifold-matching GAN (MMGAN). MMGAN finds two manifolds representing the vector representations of real and fake images. If these two manifolds match, it means that real and fake images are statistically identical. To assist the manifold-matching task, we also use i) kernel tricks to find better manifold structures, ii) moving-averaged manifolds across mini-batches, and iii) a regularizer based on correlation matrix to suppress mode collapse. We conduct in-depth experiments with three image datasets and compare with several state-of-the-art GAN models. 32.4% of images generated by the proposed MMGAN are recognized as fake images during our user study (16% enhancement compared to other state-of-the-art model). MMGAN achieved an unsupervised inception score of 7.8 for CIFAR-10.

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

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

[3]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[4]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[5]  Yoshua Bengio,et al.  Deep Directed Generative Models with Energy-Based Probability Estimation , 2016, ArXiv.

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

[7]  Yoshua Bengio,et al.  Boundary-Seeking Generative Adversarial Networks , 2017, ICLR 2017.

[8]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

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

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

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

[12]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[13]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

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

[15]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[16]  Marc G. Bellemare,et al.  The Cramer Distance as a Solution to Biased Wasserstein Gradients , 2017, ArXiv.

[17]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[18]  Vaibhava Goel,et al.  McGan: Mean and Covariance Feature Matching GAN , 2017, ICML.

[19]  Razvan Pascanu,et al.  Theano: Deep Learning on GPUs with Python , 2012 .

[20]  Michael Rabadi,et al.  Kernel Methods for Machine Learning , 2015 .

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

[22]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[24]  Hariharan Narayanan,et al.  Sample Complexity of Testing the Manifold Hypothesis , 2010, NIPS.

[25]  Gang Hua,et al.  CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[26]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[27]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.