生成式对抗网络及其计算机视觉应用研究综述

曹仰杰; 贾丽丽; 陈永霞; 林楠; 李学相

doi:10.11834/jig.180103

综述 | 浏览量 : 0 下载量: 381 CSCD: 0

PDF
导出
分享
收藏
专辑

生成式对抗网络及其计算机视觉应用研究综述
Review of computer vision based on generative adversarial networks
2018年23卷第10期页码：1433-1449
收稿：2018-03-02，

修回：2018-4-8，

纸质出版：2018-10-16
DOI： 10.11834/jig.180103
稿件说明：

移动端阅览

曹仰杰, 贾丽丽, 陈永霞, 林楠, 李学相. 生成式对抗网络及其计算机视觉应用研究综述[J]. 中国图象图形学报, 2018,23(10):1433-1449. DOI： 10.11834/jig.180103.

Yangjie Cao, Lili Jia, Yongxia Chen, Nan Lin, Xuexiang Li. Review of computer vision based on generative adversarial networks[J]. Journal of Image and Graphics, 2018, 23(10): 1433-1449. DOI： 10.11834/jig.180103.

摘要

目的

生成式对抗网络（GAN）的出现为计算机视觉应用提供了新的技术和手段，它以独特零和博弈与对抗训练的思想生成高质量的样本，具有比传统机器学习算法更强大的特征学习和特征表达能力。目前在机器视觉领域尤其是样本生成领域取得了显著的成功，是当前研究的热点方向之一。

方法

以生成式对抗网络的不同模型及其在计算机视觉领域的应用为研究对象，在广泛调研文献特别是GAN的最新发展成果基础上，结合不同模型的对比试验，对每种方法的基本思想、方法特点及使用场景进行分析，并对GAN的优势与劣势进行总结，阐述了GAN研究的现状、在计算机视觉上的应用范围，归纳生成式对抗网络在高质量图像生成、风格迁移与图像翻译、文本与图像的相互生成和图像的还原与修复等多个计算机视觉领域的研究现状和发展趋势，并对每种应用的理论改进之处、优点、局限性及使用场景进行了总结，对未来可能的发展方向进行展望。

结果

GAN的不同模型在生成样本质量与性能上各有优劣。当前的GAN模型在图像的处理上取得较大的成就，能生成以假乱真的样本，但是也存在网络不收敛、模型易崩溃、过于自由不可控的问题。

结论

GAN作为一种新的生成模型具有很高的研究价值与应用价值，但目前存在一些理论上的桎梏亟待突破，在应用方面生成高质量的样本、逼真的场景是值得研究的方向。

Abstract

Objective

The appearance of generative adversarial networks (GANs) provides a new approach and a framework for the application of computer vision.GAN generates high-quality samples with unique zero-sum game and adversarial training concepts

and therefore more powerful in both feature learning and representation than traditional machine learning algorithms.Remarkable achievements have been realized in the field of computer vision

especially in sample generation

which is one of the popular topics in current research.

Method

The research and application of different GAN models based on computer vision are reviewed based on the extensive research and the latest achievements of relevant literature.The typical GAN network methods are introduced

categorized

and compared in experiments by using generation samples to present their performance and summarized the research status and development trends in computer vision fields

such as high-quality image generation

style transfer and image translation

text-image mutual generation

image inpainting

and restoration.Finally

existing major research problems are summarized and discussed

and potential future research directions are presented.

Result

Since the emergence of GAN

many variations have been proposed for different fields

either structural improvement or development of theory or innovation in applications.Different GAN models have advantages and disadvantages in terms of generating examples

have significant achievements in many fields

especially the computer vision

and can generate examples such as the real ones.However

they also have unique problems

such as non-convergence

model collapse

and uncontrollability due to high degree-of-freedom.Priori hypotheses about the data in the original GAN

whose final goals are to realize infinite modeling power and fit for all distributions

hardly exits.In addition

the designs of GAN models are simple.A complex function model need not be pre-designed

and the generator and the discriminator can work normally with the back propagation algorithm.Moreover

GAN can use a machine to interact with other machines through continuous confrontation and learn the inherent laws in the real world with sufficient data training.Each aspect has two sides

and a series of problems are hidden behind the goal of infinite modeling.The generation process is extremely flexible that the stability and convergence of the training process cannot be guaranteed.Model collapse will likely occur and further training cannot be achieved.The original GAN has the following problems:disappearance of gradients

training difficulties

the losses of generator and discriminator cannot indicate the training process

the lack of diversities in the generated samples

and easy over-fitting.Discrete distributions are also difficult to generate due to the limitations of GAN.Many researchers have proposed new ways to address these problems

and several landmark models

such as DCGAN

CGAN

WGAN

WGAN-GP

EBGAN

BEGAN

InfoGAN

and LSGAN

have been introduced.DCGAN combines GAN with CNN and performs well in the field of computer vision.Furthermore

DCGAN sets a series of limitations for the CNN network so it can be trained stably and use the learned feature representation for sample generation and image classification.CGAN inputs the conditional variable (

) with the random variable (

) and the real data (

) to guide the data generation process.The conditional variable (

) can be category labels

texts

and generated targets.The straightforward improvement proves to be extremely effective and has been widely used in subsequent work.WGAN uses the Wasserstein distance to measure the distance between the real and generated samples instead of the JS divergence.The Wasserstein distance has the following advantages.It can measure distance even if the two distributions do not overlap

has excellent smoothing properties

and can solve the gradients disappearance problem to some degrees.In addition

WGAN solves the problems of instability in training

diversifies the generated examples

and does not require the careful balancing of the training of G and D.WGAN-GP replaces the weight pruning in WGAN to implement the Lipschitz constraint method.Experiments show that the quality of samples generated by WGAN-GP is higher than those of WGAN.It also provides stable training without hyperparameters and successfully trains various generating tasks.However

the convergence speed of WGAN-GP is slower

that is

it takes more time to converge under the same dataset.The EBGAN interprets GAN from the perspective of energy.It can learn the probability distributions of images with low convergence speed.The images BEGAN products are still disorganized

whereas other models have been able to express the outline of the objects roughly.However

the images generated by BEGAN have the sharpest edges and rich image diversities in the experiments.The discriminator of BEGAN draws lessons from EBGAN

and the loss of generator refers to the loss of WGAN.It also proposes a hyper parameter that can measure the diversity of generated samples to balance D and G and stabilize the training process.The internal texture of the generated images of InfoGAN is poor

and the shape of the generated objects is the same.As for the generator

in addition to the input noise (

)

a controllable variable (

) is added

which contains interpretable information about the data to control the generative results

resulting in poor diversity.LSGAN can generate high quality examples because the object function of least squares loss replaces the cross-entropy loss

which partly solves the two shortcomings (i.e.

low-quality and instability of training process).

Conclusion

GAN has significant theoretical and practical values as a new generative model.It provides a good solution to problems of insufficient sample

poor quality of generation

and difficulties in extracting features.GAN is an inclusive framework that can be combined with most deep learning algorithms to solve problems that traditional machine learning algorithms cannot solve.However

it has theoretical problems that must be solved urgently.How to generate high-quality examples and a realistic scene is worth studying.Further GAN developments are predicted in the following areas:breakthrough of theory

development of algorithm

system of evaluation

system of specialism

and combination of industry.

关键词

Keywords

references

Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. arXiv preprint arXiv: 1406.2661, 2014.

Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.[DOI:10.1126/science.1127647]

Sonka M, Hlavac V, Boyle R. Image Processing, Analysis and Machine Vision[M]. Boston, MA:Springer, 1993.[DOI:10.1007/978-1-4899-3216-7]

Li C, Wand M. Precomputed real-time texture synthesis with Markovian generative adversarial networks[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016: 702-716.[ DOI:10.1007/978-3-319-46487-9_43 http://dx.doi.org/10.1007/978-3-319-46487-9_43 ]

Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada: Curran Associates Inc., 2012: 1097-1105.

Cappelli R, Erol A, Maio D, et al. Synthetic fingerprint-image generation[C]//Proceedings of the 15th International Conference on Pattern Recognition. Barcelona, Spain: IEEE, 2000: 471-474.[ DOI:10.1109/icpr.2000.903586 http://dx.doi.org/10.1109/icpr.2000.903586 ]

Szeliski R. Computer Vision:Algorithms and Applications[M]. London:Springer, 2011.[DOI:10.1007/978-1-84882-935-0]

Baird H S, Coates A L, Fateman R J. PessimalPrint:a reverse Turing test[J]. International Journal on Document Analysis and Recognition, 2003, 5(2-3):158-163.[DOI:10.1007/s10032-002-0089-1]

Owechko Y. Specific emitter identification using histogram of oriented gradient features: US, US 20100061630 A1[P]. 2010-03-11.

Choi J Y, Sung K S, Yang Y K. Multiple vehicles detection and tracking based on scale-invariant feature transform[C]//Proceedings of 2007 IEEE Intelligent Transportation Systems Conference. Seattle, WA, USA: IEEE, 2007: 528-533.[ DOI:10.1109/itsc.2007.4357684 http://dx.doi.org/10.1109/itsc.2007.4357684 ]

Mo J, Walrand J. Fair end-to-end window-based congestion control[J]. IEEE/ACM Transactions on Networking, 2000, 8(5):556-567.[DOI:10.1109/90.879343]

Pu Y C, Gan Z, Henao R, et al. Variational autoencoder for deep learning of images, labels and captions[EB/OL]. 2016-09-28[2017-11-13] . https://arxiv.org/pdf/1609.08976.pdf https://arxiv.org/pdf/1609.08976.pdf .

Kingma D P, Welling M. Auto-encoding variational Bayes[EB/OL]. 2014-05-01[2017-11-19] . https://arxiv.org/pdf/1312.6114.pdf https://arxiv.org/pdf/1312.6114.pdf .

LeCun Y, Boser B, Denker J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4):541-551.[DOI:10.1162/neco.1989.1.4.541]

LeCun Y, Bottou L, Bengio Y, et al. Gradient-Based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.[DOI:10.1109/5.726791]

Graves A, Fernández S, Schmidhuber J. Multi-dimensional recurrent neural networks[C]//Proceedings of the 17th International Conference on Artificial Neural Networks. Porto, Portugal: Springer, 2007: 549-558.[ DOI:10.1007/978-3-540-74690-4_56 http://dx.doi.org/10.1007/978-3-540-74690-4_56 ]

Graves A. Long short-term memory[M]//Graves A. Supervised Sequence Labelling with Recurrent Neural Networks. Berlin, Heidelberg: Springer, 2012: 1735-1780.[ DOI:10.1007/978-3-642-24797-2_4 http://dx.doi.org/10.1007/978-3-642-24797-2_4 ]

Goodfellow I, Bengio Y, Courville A. Deep Learning[M]. Cambridge:The MIT Press, 2016:26-29.

He D, Chen W, Wang L W, et al. A game-heoretic machine learning approach for revenue maximization in sponsored search[C]//Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence.Beijing, China: AAAI, 2013: 206-212.

Ratliff L J, Burden S A, Sastry S S. Characterization and computation of local Nash equilibria in continuous games[C]//Proceedings of the 51st Annual Allerton Conference on Communication, Control, and Computing. Monticello, IL, USA: IEEE, 2013: 917-924.[ DOI:10.1109/allerton.2013.6736623 http://dx.doi.org/10.1109/allerton.2013.6736623 ]

Goodfellow I, NIPS 2016 tutorial: generative adversarial networks[EB/OL]. 2017-04-03[2018-03-01] . https://arxiv.org/pdf/1701.00160.pdf https://arxiv.org/pdf/1701.00160.pdf .

Salimans T, Goodfellow I, Zaremba W, et al. Improved techniques for training GANs[EB/OL]. 2016-06-10[2017-12-05] . https://arxiv.org/pdf/1606.03498.pdf https://arxiv.org/pdf/1606.03498.pdf .

Mirza M, Osindero S. Conditional generative adversarial nets[J]. arXiv preprint arXiv: 1411.1784, 2014.

Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL]. 2016-12-20[2018-02-28] . https://arxiv.org/pdf/1511.06434.pdf https://arxiv.org/pdf/1511.06434.pdf .

Arjovsky M, Chintala S, Bottou L. Wasserstein GAN[EB/OL]. 2017-12-06[2018-02-23] . https://arxiv.org/pdf/1701.07875.pdf https://arxiv.org/pdf/1701.07875.pdf .

Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of Wasserstein GANs[EB/OL]. 2017-12-25[2018-01-19] . https://arxiv.org/pdf/1704.00028.pdf https://arxiv.org/pdf/1704.00028.pdf .

Zeiler M D, Taylor G W, Fergus R. Adaptive deconvolutional networks for mid and high level feature learning[C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2018-2025.[ DOI:10.1109/iccv.2011.6126474 http://dx.doi.org/10.1109/iccv.2011.6126474 ]

Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille, France: JMLR, 2015: 448-456.

Kingma D P, Ba J. Adam: a method for stochastic optimization[J]. arXiv preprint arXiv: 1412.6980, 2014.

Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines[C]//Proceedings of the 27thInternational Conference on International Conference on Machine Learning. Haifa, Israel: Omnipress, 2010: 807-814.

Xu B, Wang N Y, Chen T Q, et al. Empirical evaluation of rectified activations in convolutional network[EB/OL] . 2015-11-27[2018-0-1-28]. https://arxiv.org/pdf/1505.00853.pdf https://arxiv.org/pdf/1505.00853.pdf .

Wang K F, Gou C, Duan Y J, et al. Gener ative adversarial networks:the state of the art and beyond[J]. Acta Automatica Sinica, 2017, 43(3):321-332.

王坤峰, 苟超, 段艳杰, 等.生成式对抗网络GAN的研究进展与展望[J].自动化学报, 2017, 43(3):321-332. [DOI:10.16383/j.aas.2017.y000003]

郑华滨.令人拍案叫绝的Wasserstein GAN[EB/OL]. 2017-04-02[2018-01-20] . https://zhuanlan.zhihu.com/p/25071913 https://zhuanlan.zhihu.com/p/25071913 .

Zhao J B, Mathieu M, LeCun Y. Energy-based generative adversarial network[EB/OL]. 2017-03-06[2017-12-23] . https://arxiv.org/pdf/1609.03126.pdf https://arxiv.org/pdf/1609.03126.pdf .

Berthelot D, Schumm T, Metz L. BEGAN: boundary equilibrium generative adversarial networks[EB/OL]. 2017-05-31[2018-01-08] . https://arxiv.org/pdf/1703.10717.pdf https://arxiv.org/pdf/1703.10717.pdf .

Chen X, Duan Y, Houthooft R, et al. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets[EB/OL]. 2016-06-12[2017-12-27] . https://arxiv.org/pdf/1606.03657.pdf https://arxiv.org/pdf/1606.03657.pdf .

Mao X D, Li Q, Xie H R, et al. Least squares generative adversarial networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2018: 2813-2821.[ DOI:10.1109/ICCV.2017.304 http://dx.doi.org/10.1109/ICCV.2017.304 ]

Hwalsuklee. Tensorflow-generative-model-collections[EB/OL]. 2017-09-06[2017-10-19] . https://github.com/hwalsuklee/tensorflow-generative-model-collections https://github.com/hwalsuklee/tensorflow-generative-model-collections .

Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms[EB/OL]. 2017-09-15[2018-02-23] . https://arxiv.org/pdf/1708.07747.pdf https://arxiv.org/pdf/1708.07747.pdf .

Zhang H, Xu T, Li H S, et al. StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 5908-5916.[ DOI:10.1109/iccv.2017.629 http://dx.doi.org/10.1109/iccv.2017.629 ]

Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA: IEEE, 2009: 248-255.[ DOI:10.1109/CVPR.2009.5206848 http://dx.doi.org/10.1109/CVPR.2009.5206848 ]

Denton E, Chintala S, Szlam A, et al. Deep generative image models using a Laplacian pyramid of adversarial networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press, 2015: 1486-1494.

Isola P. Zhu J Y, Zhou T H, et al. Image-to-Image translation with conditional adversarial networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 5967-5976.[ DOI:10.1109/CVPR.2017.632 http://dx.doi.org/10.1109/CVPR.2017.632 ]

Ronneberger O. Invited Talk: U-Net convolutional networks for biomedical image segmentation[M]//Maier-Hein K H, Fritzsche G, Deserno T M, et al. Bildverarbeitung für die Medizin 2017. Berlin, Heidelberg: Springer, 2017.[ DOI:10.1007/978-3-662-54345-0_3 http://dx.doi.org/10.1007/978-3-662-54345-0_3 ]

Zhu J Y, Park T, Isola P, et al. Unpaired Image-to-Image translation using cycle-consistent adversarial networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 2242-2251.[ DOI:10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244 ]

Kim T, Cha M, Kim H, et al. Learning to discover cross-domain relations with generative adversarial networks[C]//Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia: PMLR, 2017.

Taigman Y, Polyak A, Wolf L. Unsupervised cross-domain image generation[EB/OL]. 2016-11-07[2017-12-24] . https://arxiv.org/pdf/1611.02200.pdf https://arxiv.org/pdf/1611.02200.pdf .

Liu M Y, Tuzel O. Coupled generative adversarial networks[EB/OL]. 2016-09-20[2018-01-12] . https://arxiv.org/pdf/1606.07536.pdf https://arxiv.org/pdf/1606.07536.pdf .

Bousmalis K, Silberman N, Dohan D, et al. Unsupervised pixel-level domain adaptationwith generative adversarial networks[C] //Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 95-104.[ DOI:10.1109/CVPR.2017.18 http://dx.doi.org/10.1109/CVPR.2017.18 ]

Reed S, Akata Z, Yan X C, et al. Generative adversarial text to image synthesis[C]//Proceedings of the 33rd International Conference on Machine Learning. New York, USA: JML, 2016: 1060-1069.

Liang X D, Hu Z T, Zhang H, et al. Recurrent topic-transition GAN for visual paragraph generation[EB/OL]. 2017-03-23[2018-01-08] . https://arxiv.org/pdf/1703.07022.pdf https://arxiv.org/pdf/1703.07022.pdf .

Huang R, Zhang S, Li T Y, et al. Beyond face rotation: global and local perception GAN for photorealistic and identity preserving frontal view synthesis[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 2458-2467.[ DOI:10.1109/ICCV.2017.267 http://dx.doi.org/10.1109/ICCV.2017.267 ]

Yeh R A, Chen C, Lim T Y, et al. Semantic image inpainting with deep generative models[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 6882-6890.[ DOI:10.1109/CVPR.2017.728 http://dx.doi.org/10.1109/CVPR.2017.728 ]

Pathak D, Krähenbühl P, Donahue J, et al. Context encoders: feature learning by inpainting[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 2536-2544.[ DOI:10.1109/CVPR.2016.278 http://dx.doi.org/10.1109/CVPR.2016.278 ]

Li Y J, Liu S F, Yang J M, et al. Generative face completion[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 5892-5900.[ DOI:10.1109/CVPR.2017.624 http://dx.doi.org/10.1109/CVPR.2017.624 ]

Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 105-114.[ DOI:10.1109/CVPR.2017.19 http://dx.doi.org/10.1109/CVPR.2017.19 ]

Kupyn O, Budzan V, Mykhailych M, et al. DeblurGAN: blind motion deblurring using conditional adversarial networks[EB/OL]. 2018-04-03[2018-03-27] . https://arxiv.org/pdf/1711.07064.pdf https://arxiv.org/pdf/1711.07064.pdf .

Shrivastava A, Pfister T, Tuzel O, et al. Learning from simulated and unsupervised images through adversarial training[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 2242-2251.[ DOI:10.1109/CVPR.2017.241 http://dx.doi.org/10.1109/CVPR.2017.241 ]

Mathieu M, Couprie C, LeCun Y. Deep multi-scale video prediction beyond mean square error[EB/OL]. 2016-02-26[2017-12-19] . https://arxiv.org/pdf/1511.05440.pdf https://arxiv.org/pdf/1511.05440.pdf .

Vondrick C, Pirsiavash H, Torralba A. Generating videos with scene dynamics[EB/OL]. 2016-10-26[2017-12-23] . https://arxiv.org/pdf/1609.02612.pdf https://arxiv.org/pdf/1609.02612.pdf .

Tulyakov S, Liu M Y, Yang X D, et al. MoCoGAN: decomposing motion and content for video generation[EB/OL]. 2017-12-14[2018-02-17] . https://arxiv.org/abs/1707.04993 https://arxiv.org/abs/1707.04993 .

Li J A, Liang X D, Wei Y C, et al. Perceptual generative adversarial networks for small object detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 1951-1959.[ DOI:10.1109/CVPR.2017.211 http://dx.doi.org/10.1109/CVPR.2017.211 ]

Yang L C, Chou S Y, Yang Y H. MidiNet: a convolutional generative adversarial network for symbolic-domain music generation[EB/OL]. 2017-07-18[2017-12-22] . https://arxiv.org/pdf/1703.10847.pdf https://arxiv.org/pdf/1703.10847.pdf .

Esteban C, Hyland S L, Rätsch G. Real-valued (Medical) time series generation with recurrent conditional GANs[EB/OL]. 2017-12-04[2018-02-04] . https://arxiv.org/pdf/1706.02633.pdf https://arxiv.org/pdf/1706.02633.pdf .

Choi E, Biswal S, Malin B, et al. Generating Multi-label discrete electronic health records using generative adversarial network[EB/OL]. 2018-01-11[2018-01-28] . https://arxiv.org/pdf/1703.06490v1.pdf https://arxiv.org/pdf/1703.06490v1.pdf .

Wu J J, Zhang C K, Xue T F, et al. Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling[EB/OL]. 2017-01-04[2017-12-26] . https://arxiv.org/abs/1610.07584.pdf https://arxiv.org/abs/1610.07584.pdf .

Park E, Yang J M, Yumer E, et al. Transformation-grounded image generation network for novel 3D view synthesis[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 702-711.[ DOI:10.1109/cvpr.2017.82 http://dx.doi.org/10.1109/cvpr.2017.82 ]

Gong M G, Niu X D, Zhang P Z, et al. Generative adversarial networks for change detection in multispectral imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(12):2310-2314.[DOI:10.1109/lgrs.2017.2762694]

Gurumurthy S, Sarvadevabhatla R K, Babu R V. DeLiGAN: generative adversarial networks for diverse and limited data[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 4941-4949.[ DOI:10.1109/CVPR.2017.525 http://dx.doi.org/10.1109/CVPR.2017.525 ]

Xue Y, Xu T, Zhang H, et al. SegAN: adversarial network with multi-scale L 1 loss for medical image segmentation[EB/OL]. 2017-07-16[2018-01-26] . https://arxiv.org/pdf/1706.01805.pdf https://arxiv.org/pdf/1706.01805.pdf ..

Ghosh A, Bhattacharya B, Chowdhury S B R. SAD-GAN: synthetic autonomous driving using generative adversarial networks[EB/OL]. 2016-11-27[2018-01-29] . https://arxiv.org/pdf/1611.08788.pdf https://arxiv.org/pdf/1611.08788.pdf .