Abstract
The labeled training data are very rare in actual environment. Generating new data based on given label is one of the most commonly approaches in data augmentation. This paper proposes a new data augmentation model that can extract the deformation features between the given deformation image and the original image. The model generates similar images to the given deformation images according to the deformation feature. The model can keep the new generation images have the same probability distribution as the given deformation images. Experiments on MNIST and CIFAR-10 prove that the new deformation images can get a similar classification accuracy with the given deformation images, which proves that the new sample is effective.
This work was supported by the National Science Foundation of China (Grant No. 61625204), partially supported by the State Key Program of National Science Foundation of China (Grant No. 61432012 and 61432014).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baird, H.S.: Document image defect models. In: Baird, H.S., Bunke, H., Yamamoto, K. (eds.) Structured Document Image Analysis. Springer, Heidelberg (1992). https://doi.org/10.1007/978-3-642-77281-8_26
Simard, P., Victorri, B., Cun, Y. L., Denker, J.: Tangent Prop: a formalism for specifying selected invariances in an adaptive network. In: International Conference on Neural Information Processing Systems, pp. 895–903 (1991)
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition, p. 958 (2003)
Hauberg, S., Freifeld, O., Larsen, A.B.L., Fisher Iii, J.W., Hansen, L.K.: Dreaming more data: class-dependent distributions over diffeomorphisms for learned data augmentation. In: Computer Science (2015)
Grenander, U.: General Pattern Theory: A Mathematical Study of Regular Structures. Clarendon Press, New York (1993)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097–1105 (2012)
Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network, pp. 2366–2374 (2014)
Jaitly, N., Hinton, G.E.: Vocal tract length perturbation (VTLP) improves speech recognition. In: ICML Workshop on Deep Learning for Audio, Speech and Language, p. 958 (2013)
Loosli, G., Canu, S., Bottou, L.: Invariant SVM using selective sampling training invariant support vector machines using selective sampling, pp. 301–320 (2014)
Taylor: Modeling human motion using binary latent variables. In: International Conference on Neural Information Processing Systems, pp. 1345–1352 (2006)
Memisevic, R., Hinton, G.: Unsupervised learning of image transformations. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8 (2007)
Memisevic, R., Hinton, G.E.: Learning to represent spatial transformations with factored higher-order Boltzmann machines. Neural Comput. 22(6), 1473–1492 (2010)
Pu, Y., et al.: Adversarial symmetric variational autoencoder (2017)
Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models, pp. 1278–1286 (2014)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes (2013)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2014)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning (2016)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning (2017)
Edwards, H., Storkey, A.: Towards a neural statistician (2016)
Agostinelli, F., Hoffman, M., Sadowski, P., Baldi, P.: Learning activation functions to improve deep neural networks. In: Computer Science (2015)
Graham, B.: Fractional max-pooling. Eprint Arxiv (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Xia, L., Lv, J., Xu, Y. (2018). A Data Augmentation Model Based on Variational Approach. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11302. Springer, Cham. https://doi.org/10.1007/978-3-030-04179-3_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-04179-3_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04178-6
Online ISBN: 978-3-030-04179-3
eBook Packages: Computer ScienceComputer Science (R0)