Introspective Generative Modeling: Decide Discriminatively

We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capable of introspection: being able to self-evaluate the difference between its generated samples and the given training data. When followed by repeated discriminative learning, desirable properties of modern discriminative classifiers are directly inherited by the generator. IGM learns a cascade of CNN classifiers using a synthesis-by-classification algorithm. In the experiments, we observe encouraging results on a number of applications including texture modeling, artistic style transferring, face modeling, and semi-supervised learning.

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

[2]  Jun S. Liu,et al.  Monte Carlo strategies in scientific computing , 2001 .

[3]  Andrea Vedaldi,et al.  Texture Networks: Feed-forward Synthesis of Textures and Stylized Images , 2016, ICML.

[4]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[5]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[6]  Andrew Brock,et al.  Neural Photo Editing with Introspective Adversarial Networks , 2016, ICLR.

[7]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

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

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

[10]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Geoffrey E. Hinton,et al.  Self Supervised Boosting , 2002, NIPS.

[12]  Zhuowen Tu,et al.  Introspective Classifier Learning: Empower Generatively , 2017, ArXiv.

[13]  Tianqi Chen,et al.  Stochastic Gradient Hamiltonian Monte Carlo , 2014, ICML.

[14]  Zhuowen Tu,et al.  Learning Generative Models via Discriminative Approaches , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[16]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

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

[18]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[19]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

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

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Yang Lu,et al.  A Theory of Generative ConvNet , 2016, ICML.

[23]  Michael I. Jordan,et al.  An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators , 2008, ICML '08.

[24]  Song-Chun Zhu,et al.  Equivalence of Julesz Ensembles and FRAME Models , 2000, International Journal of Computer Vision.

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

[26]  John D. Lafferty,et al.  Inducing Features of Random Fields , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

[28]  Tony Jebara,et al.  Machine learning: Discriminative and generative , 2006 .

[29]  David M. Blei,et al.  Stochastic Gradient Descent as Approximate Bayesian Inference , 2017, J. Mach. Learn. Res..

[30]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

[31]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[32]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[33]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[34]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[35]  Yee Whye Teh,et al.  Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[36]  Paul M. Thompson,et al.  Brain Anatomical Structure Segmentation by Hybrid Discriminative/Generative Models , 2008, IEEE Transactions on Medical Imaging.

[37]  Ulf Grenander,et al.  General Pattern Theory: A Mathematical Study of Regular Structures , 1993 .

[38]  Alan L. Yuille,et al.  Feature extraction from faces using deformable templates , 2004, International Journal of Computer Vision.

[39]  Pierre Baldi,et al.  Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[40]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[41]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

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

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

[44]  A. Yuille,et al.  Opinion TRENDS in Cognitive Sciences Vol.10 No.7 July 2006 Special Issue: Probabilistic models of cognition Vision as Bayesian inference: analysis by synthesis? , 2022 .

[45]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.