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

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

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

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

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

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

[7]  Frank Gabel Generative Adversarial Text-to-Image Synthesis , 2018 .

[8]  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).

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

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

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

[12]  Xinyun Chen Under Review as a Conference Paper at Iclr 2017 Delving into Transferable Adversarial Ex- Amples and Black-box Attacks , 2016 .

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

[14]  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).

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

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

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

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

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

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

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

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

[23]  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 .

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

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

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

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