Distributional Adversarial Networks

We propose a framework for adversarial training that relies on a sample rather than a single sample point as the fundamental unit of discrimination. Inspired by discrepancy measures and two-sample tests between probability distributions, we propose two such distributional adversaries that operate and predict on samples, and show how they can be easily implemented on top of existing models. Various experimental results show that generators trained with our distributional adversaries are much more stable and are remarkably less prone to mode collapse than traditional models trained with pointwise prediction discriminators. The application of our framework to domain adaptation also results in considerable improvement over recent state-of-the-art.

[1]  Kilian Q. Weinberger,et al.  Marginalized Denoising Autoencoders for Domain Adaptation , 2012, ICML.

[2]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  E. Lehmann.  Testing Statistical Hypotheses , 1960 .

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

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

[6]  Bernhard Schölkopf,et al.  AdaGAN: Boosting Generative Models , 2017, NIPS.

[7]  Yiming Yang,et al.  MMD GAN: Towards Deeper Understanding of Moment Matching Network , 2017, NIPS.

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

[9]  Le Song,et al.  A Hilbert Space Embedding for Distributions , 2007, IFIP Working Conference on Database Semantics.

[10]  Richard S. Zemel,et al.  Generative Moment Matching Networks , 2015, ICML.

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

[12]  Bernhard Schölkopf,et al.  Measuring Statistical Dependence with Hilbert-Schmidt Norms , 2005, ALT.

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

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

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

[16]  Antonio Torralba,et al.  Generating Videos with Scene Dynamics , 2016, NIPS.

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

[18]  Bernhard Schölkopf,et al.  Kernel Measures of Conditional Dependence , 2007, NIPS.

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

[20]  Edwin Lughofer,et al.  Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning , 2017, ICLR.

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

[22]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[23]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

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

[25]  Alexander J. Smola,et al.  Deep Sets , 2017, 1703.06114.

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

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

[28]  John E. Hopcroft,et al.  Stacked Generative Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Yu Liu,et al.  Quality Aware Network for Set to Set Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Dimitris N. Metaxas,et al.  StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[32]  Le Song,et al.  A Hilbert Space Embedding for Distributions , 2007, Discovery Science.

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

[34]  Barnabás Póczos,et al.  Deep Learning with Sets and Point Clouds , 2016, ICLR.

[35]  Zoubin Ghahramani,et al.  Training generative neural networks via Maximum Mean Discrepancy optimization , 2015, UAI.

[36]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

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

[38]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[39]  Alexander J. Smola,et al.  Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy , 2016, ICLR.

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

[41]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[42]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

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