Mode Regularized Generative Adversarial Networks

Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models. We also show that our regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.

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

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

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

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

[5]  Thomas Brox,et al.  Generating Images with Perceptual Similarity Metrics based on Deep Networks , 2016, NIPS.

[6]  Yann LeCun,et al.  Deep multi-scale video prediction beyond mean square error , 2015, ICLR.

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

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

[9]  Tamara L. Berg,et al.  Learning Temporal Transformations from Time-Lapse Videos , 2016, ECCV.

[10]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[11]  Omer Levy,et al.  Published as a conference paper at ICLR 2018 S IMULATING A CTION D YNAMICS WITH N EURAL P ROCESS N ETWORKS , 2018 .

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

[13]  Shunta Saito,et al.  Temporal Generative Adversarial Nets with Singular Value Clipping , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

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

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

[16]  Masaki Saito,et al.  Temporal Generative Adversarial Nets , 2016, ArXiv.

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

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

[19]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[21]  Lucas Theis,et al.  Amortised MAP Inference for Image Super-resolution , 2016, ICLR.

[22]  Alexei A. Efros,et al.  Generative Visual Manipulation on the Natural Image Manifold , 2016, ECCV.

[23]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[24]  Chuan Li,et al.  Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks , 2016, ECCV.

[25]  Yoshua Bengio,et al.  Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).