Generating Images Part by Part with Composite Generative Adversarial Networks

Image generation remains a fundamental problem in artificial intelligence in general and deep learning in specific. The generative adversarial network (GAN) was successful in generating high quality samples of natural images. We propose a model called composite generative adversarial network, that reveals the complex structure of images with multiple generators in which each generator generates some part of the image. Those parts are combined by alpha blending process to create a new single image. It can generate, for example, background and face sequentially with two generators, after training on face dataset. Training was done in an unsupervised way without any labels about what each generator should generate. We found possibilities of learning the structure by using this generative model empirically.

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

[2]  Daan Wierstra,et al.  Towards Conceptual Compression , 2016, NIPS.

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

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

[5]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[6]  Ruslan Salakhutdinov,et al.  Generating Images from Captions with Attention , 2015, ICLR.

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

[8]  Yuting Zhang,et al.  Learning to Disentangle Factors of Variation with Manifold Interaction , 2014, ICML.

[9]  M. V. Rossum,et al.  In Neural Computation , 2022 .

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

[11]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

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

[13]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[14]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

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

[16]  Hui Jiang,et al.  Generating images with recurrent adversarial networks , 2016, ArXiv.

[17]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

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

[19]  Abhinav Gupta,et al.  Generative Image Modeling Using Style and Structure Adversarial Networks , 2016, ECCV.

[20]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

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

[22]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[24]  L. Christophorou.  Science , 2018, Emerging Dynamics: Science, Energy, Society and Values.

[25]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[26]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.