Improving Generative Adversarial Networks With Local Coordinate Coding

Generative adversarial networks (GANs) have shown remarkable success in generating realistic data from some predefined prior distributions. However, such prior distributions are often independent of real data and thus may lose semantic information of data. In practice, the semantic information might be represented by some latent distribution learned from data. However, such latent distribution may incur difficulties in data sampling for GAN methods. In this paper, rather than sampling from the predefined prior distribution, we propose a local coordinate coding GAN (LCCGAN-v1) to improve the performance of GANs. First, we propose a local coordinate coding (LCC)-based sampling method to sample points from the latent manifold. With the LCC sampling method, we can exploit the local information on the latent manifold and thus produce new data with promising quality. Second, we propose an advanced LCCGAN-v2 by introducing a higher-order term in the generator approximation. This term is able to achieve better approximation and thus further improve the performance. More critically, we derive the generalization bound for both LCCGAN-v1 and LCCGAN-v2 and prove that a small-dimensional input is sufficient to achieve good generalization performance. Extensive experiments on four benchmark datasets demonstrate the superiority of the proposed method over existing GAN methods.

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

[2]  Yingyu Liang,et al.  Generalization and Equilibrium in Generative Adversarial Nets (GANs) , 2017, ICML.

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

[4]  Yihong Gong,et al.  Nonlinear Learning using Local Coordinate Coding , 2009, NIPS.

[5]  Jiebo Luo,et al.  Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yinda Zhang,et al.  LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop , 2015, ArXiv.

[7]  Andrea Vedaldi,et al.  Adversarial Generator-Encoder Networks , 2017, ArXiv.

[8]  Shiyu Chang,et al.  AutoGAN: Neural Architecture Search for Generative Adversarial Networks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

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

[11]  Qingyao Wu,et al.  Auto-Embedding Generative Adversarial Networks For High Resolution Image Synthesis , 2019, IEEE Transactions on Multimedia.

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

[13]  Tao Xu,et al.  On the Discrimination-Generalization Tradeoff in GANs , 2017, ICLR.

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

[15]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[16]  Stefano Berretti,et al.  Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  John Langford,et al.  Multi-Label Prediction via Compressed Sensing , 2009, NIPS.

[18]  Francis R. Bach,et al.  Breaking the Curse of Dimensionality with Convex Neural Networks , 2014, J. Mach. Learn. Res..

[19]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[20]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[21]  Hao Hu,et al.  Global Versus Localized Generative Adversarial Nets , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[23]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[24]  Tong Zhang,et al.  Improved Local Coordinate Coding using Local Tangents , 2010, ICML.

[25]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[26]  Mingkui Tan,et al.  NAT: Neural Architecture Transformer for Accurate and Compact Architectures , 2019, NeurIPS.

[27]  Marc'Aurelio Ranzato,et al.  Video (language) modeling: a baseline for generative models of natural videos , 2014, ArXiv.

[28]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[29]  Truyen Tran,et al.  Improving Generalization and Stability of Generative Adversarial Networks , 2019, ICLR.

[30]  Mingkui Tan,et al.  Multi-marginal Wasserstein GAN , 2019, NeurIPS.

[31]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[32]  Qingyao Wu,et al.  Adversarial Learning with Local Coordinate Coding , 2018, ICML.

[33]  Yang Liu,et al.  Physics-Based Generative Adversarial Models for Image Restoration and Beyond , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[35]  Zhen Wang,et al.  On the Effectiveness of Least Squares Generative Adversarial Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Wei Chen,et al.  DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[39]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[40]  Xiaogang Wang,et al.  StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

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

[43]  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).

[44]  M. Talagrand,et al.  Probability in Banach Spaces: Isoperimetry and Processes , 1991 .

[45]  Fengda Zhu,et al.  Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Mingkui Tan,et al.  Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss , 2018, ArXiv.

[47]  Chuan Chen,et al.  Learning Semantic Representations for Unsupervised Domain Adaptation , 2018, ICML.

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

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

[50]  Feng Liu,et al.  On Computation and Generalization of Generative Adversarial Networks under Spectrum Control , 2019, ICLR.

[51]  Mingkui Tan,et al.  Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[53]  Takeru Miyato,et al.  cGANs with Projection Discriminator , 2018, ICLR.

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

[55]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

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

[57]  Peter L. Bartlett,et al.  Rademacher and Gaussian Complexities: Risk Bounds and Structural Results , 2003, J. Mach. Learn. Res..