Learning Fast Converging, Effective Conditional Generative Adversarial Networks with a Mirrored Auxiliary Classifier

Training conditional generative adversarial networks (GANs) has been remaining as a challenging task, though standard GANs have developed substantially and gained huge successes in recent years. In this paper, we propose a novel conditional GAN architecture with a mirrored auxiliary classifier (MAC-GAN) in its discriminator for the purpose of label conditioning. Unlike existing works, our mirrored auxiliary classifier contains both a real and a fake node for each specific class to distinguish real samples from generated samples that are assigned into the same category by previous models. Comparing with previous auxiliary classifier-based conditional GANs, our MAC-GAN learns a fast converging model for high-quality image generation, taking benefits from its robust, newly designed auxiliary classifier. Experiments on multiple benchmark datasets illustrate that our proposed model improves the quality of image synthesis compared with state-of-the-art approaches. Moreover, much better classification performance can be achieved with the mirrored auxiliary classifier, which can in turn promote the use of MAC-GAN in various transfer learning tasks.

[1]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Trung Le,et al.  Learning Generative Adversarial Networks from Multiple Data Sources , 2019, IJCAI.

[3]  Fang Zhao,et al.  Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis , 2017, NIPS.

[4]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[6]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[7]  Shuicheng Yan,et al.  Multi-Human Parsing Machines , 2018, ACM Multimedia.

[8]  Ole Winther,et al.  Ladder Variational Autoencoders , 2016, NIPS.

[9]  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).

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

[11]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Pascal Vincent,et al.  Quickly Generating Representative Samples from an RBM-Derived Process , 2011, Neural Computation.

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

[14]  Hairong Qi,et al.  Fast-Converging Conditional Generative Adversarial Networks for Image Synthesis , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[15]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[16]  Michael R. Lyu,et al.  Parallel Wasserstein Generative Adversarial Nets with Multiple Discriminators , 2019, IJCAI.

[17]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[18]  Shuicheng Yan,et al.  Recognizing Profile Faces by Imagining Frontal View , 2019, International Journal of Computer Vision.

[19]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

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

[21]  Wei Yu,et al.  Learning a Generative Model for Fusing Infrared and Visible Images via Conditional Generative Adversarial Network with Dual Discriminators , 2019, IJCAI.

[22]  Takuhiro Kaneko,et al.  Label-Noise Robust Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Christoph Meinel,et al.  microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination , 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

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

[25]  Zi Wang,et al.  Towards Efficient Convolutional Neural Networks Through Low-Error Filter Saliency Estimation , 2019, PRICAI.

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

[27]  Zi Wang,et al.  Cellular structure image classification with small targeted training samples , 2019, bioRxiv.

[28]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[29]  Jiande Sun,et al.  Eye Recognition With Mixed Convolutional and Residual Network (MiCoRe-Net) , 2018, IEEE Access.

[30]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

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

[32]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Trung Le,et al.  Dual Discriminator Generative Adversarial Nets , 2017, NIPS.

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

[35]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[36]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[37]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.

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

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

[40]  一樹 美添,et al.  5分で分かる! ? 有名論文ナナメ読み:Silver, D. et al. : Mastering the Game of Go without Human Knowledge , 2018 .

[41]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[42]  Samuel J. Yang,et al.  In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images , 2018, Cell.

[43]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[45]  Federico Vaggi,et al.  GANs for Biological Image Synthesis , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[46]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[47]  Zi Wang,et al.  Deep reinforcement learning of cell movement in the early stage of C.elegans embryogenesis , 2018, Bioinform..