Application of generative deep learning models for approximation of image distribution density

Yashchenko, А.V., Potapov, A.S., Rodionov, S.А., Zhdanov, I.N., Shcherbakov, O.V., Peterson, M.V.

Full text «Opticheskii Zhurnal»

Full text on elibrary.ru

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Ященко А.В., Потапов А.С., Родионов С.А., Жданов И.Н., Щербаков О.В., Петерсон М.В. Применение генеративных моделей глубокого обучения для аппроксимации плотности распределения образов // Оптический журнал. 2019. Т. 86. № 12. С. 29–34. http://doi.org/10.17586/1023-5086-2019-86-12-29-34

Yashchenko A.V., Potapov A.S., Rodionov S.A., Zhdanov I.N., Shcherbakov O.V., Peterson M.V. Application of generative deep learning models for approximation of image distribution density [in Russian] // Opticheskii Zhurnal. 2019. V. 86. № 12. P. 29–34. http://doi.org/10.17586/1023-5086-2019-86-12-29-34

For citation (Journal of Optical Technology):

A. V. Yashchenko, A. S. Potapov, S. A. Rodionov, I. N. Zhdanov, O. V. Shcherbakov, and M. V. Peterson, "Application of generative deep learning models for approximation of image distribution density," Journal of Optical Technology. 86(12), 769-773 (2019). https://doi.org/10.1364/JOT.86.000769

Abstract:

Generative neural network models for visual concept learning and the problem of approximating image distribution density are studied. A criterion for an image to belong to a simulated class is introduced based on an estimate of the probability in the space of latent variables and reconstruction errors. Several generative deep learning models are compared. Quality estimates of the solution to the problem of one-class classifications for a set of images of handwritten digits are experimentally obtained.

Keywords:

visual concept learning, deep learning, generative models, novelty detection

OCIS codes: 150.1135, 100.4996

References:

1. D. P. Kingma and M. Welling, “Auto-encoding variational Bayes,” in Abstracts of the International Conference on Learning Representations, Banff, Canada, April 14–16, 2014.
2. J. Goodfellow, A. Courville, and I. Benggio, Deep Learning (DMK Press, Moscow, 2018).
3. A. Makhzani, J. Shlens, N. Jaitly, and I. Goodfellow, “Adversarial autoencoders,” in Abstracts of the International Conference on Learning Representations, San Juan, Puerto Rico, May 2–4, 2016.
4. M. Tschannen, O. Bachem, and M. Lucic, “Recent advances in autoencoder-based representation learning,” in Abstracts of the Conference on Neural Information Processing Systems, Montreal, Canada, Dec. 3–4, 2018.
5. J. Zhang, H. Dang, L. H. Kuan, and E. Chang, “Flipped-adversarial autoencoders,” arXiv:1802.04504 (2018).
6. J. Donahue, P. Krähenbühl, and T. Darrell, “Adversarial feature learning,” in Abstracts of the International Conference on Learning Representations, Toulon, France, April 24–26, 2017.
7. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” in Abstracts of the Neural Information Processing Systems Conference, Montreal, Canada, Dec. 8–13, 2014.
8. S. Pidhorskyi, R. Almohsen, A. D. Adjeroh, and G. Doretto, “Generative probabilistic novelty detection with adversarial autoencoders,” in Abstracts of the Conference on Neural Information Processing Systems, Montreal, Canada, Dec. 8–13, 2018.
9. A. Dosovitskiy and T. Brox, “Generating images with perceptual similarity metrics based on deep networks,” arXiv:1602.02644 (2016).
10. P. Isola, J. Zhu, T. Zhou, and A. Efros, “Image-to-image translation with conditional adversarial networks,” in Abstracts of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, July 21–26, 2017.
11. X. Chen, Y. Duan, R. Houthooft, J. Schulman, I. Sutskever, and P. Abbeel, “InfoGAN: interpretable representation learning by information maximizing generative adversarial nets,” in Abstracts of the Neural Information Processing Systems Conference, Barcelona, Spain, Dec. 5–10, 2016.
12. D. Bang and H. Shim, “High quality bidirectional generative adversarial networks,” arXiv:1805.10717 (2018).
13. Y. Le Cun, C. Cortes, and C. J. C. Burges, “The MNIST database of handwritten digits,” http://yann.lecun.com/exdb/mnist/.
14. S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in Abstracts of the International Conference on Machine Learning, Lille, France, July 6–11, 2015.
15. D. Pedamonti, “Comparison of non-linear activation functions for deep neural networks on MNIST classification task,” arXiv:1804.02763 (2018).
16. S. Sehgal, H. Singh, and M. Agarwal, “Data analysis using principal component analysis,” in Abstracts of the International Conference on Medical Imaging, Greater Noida, India, Nov. 7–8, 2014.
17. C. Bishop, Pattern Recognition and Machine Learning (Springer, New York, 2007).
18. I. Higgins, L. Matthey, and A. Pal, “Beta-VAE: learning basic visual concepts with a constrained variational framework,” in Abstracts of the International Conference on Learning Representations, Toulon, France, April 24–26, 2017.