HGAN: Hybrid Generative Adversarial Network

In this paper, we present a simple approach to train Generative Adversarial Networks (GANs) in order to avoid a \textit {mode collapse} issue. Implicit models such as GANs tend to generate better samples compared to explicit models that are trained on tractable data likelihood. However, GANs overlook the explicit data density characteristics which leads to undesirable quantitative evaluations and mode collapse. To bridge this gap, we propose a hybrid generative adversarial network (HGAN) for which we can enforce data density estimation via an autoregressive model and support both adversarial and likelihood framework in a joint training manner which diversify the estimated density in order to cover different modes. We propose to use an adversarial network to \textit {transfer knowledge} from an autoregressive model (teacher) to the generator (student) of a GAN model. A novel deep architecture within the GAN formulation is developed to adversarially distill the autoregressive model information in addition to simple GAN training approach. We conduct extensive experiments on real-world datasets (i.e., MNIST, CIFAR-10, STL-10) to demonstrate the effectiveness of the proposed HGAN under qualitative and quantitative evaluations. The experimental results show the superiority and competitiveness of our method compared to the baselines.

[1]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[2]  Hao Chen,et al.  MagNet: A Two-Pronged Defense against Adversarial Examples , 2017, CCS.

[3]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[4]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[5]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[6]  Stefan Winkler,et al.  Autoregressive Generative Adversarial Networks , 2018, International Conference on Learning Representations.

[7]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.

[8]  Ananthram Swami,et al.  Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks , 2015, 2016 IEEE Symposium on Security and Privacy (SP).

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

[10]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[11]  Matthias Bethge,et al.  A note on the evaluation of generative models , 2015, ICLR.

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

[13]  Sebastian Nowozin,et al.  f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization , 2016, NIPS.

[14]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

[15]  Ferenc Huszar,et al.  How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary? , 2015, ArXiv.

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

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

[18]  Yiannis Demiris,et al.  MAGAN: Margin Adaptation for Generative Adversarial Networks , 2017, ArXiv.

[19]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[20]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Philip H. S. Torr,et al.  Multi-agent Diverse Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[24]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

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

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

[27]  Sridhar Mahadevan,et al.  Generative Multi-Adversarial Networks , 2016, ICLR.

[28]  Marc G. Bellemare,et al.  Count-Based Exploration with Neural Density Models , 2017, ICML.

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

[30]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[31]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[32]  Stefano Ermon,et al.  Flow-GAN: Combining Maximum Likelihood and Adversarial Learning in Generative Models , 2017, AAAI.

[33]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

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

[35]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[36]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[38]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

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

[40]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[41]  Trung Le,et al.  MGAN: Training Generative Adversarial Nets with Multiple Generators , 2018, ICLR.

[42]  Hyunjung Shim,et al.  MGGAN: Solving Mode Collapse Using Manifold-Guided Training , 2018, 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).

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

[44]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

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

[46]  Rama Chellappa,et al.  Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models , 2018, ICLR.

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

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