Empirical Evaluation of the Effectiveness of Variational Autoencoders on Data Augmentation for the Image Classification Problem
DOI:
https://doi.org/10.18201/ijisae.2020261593Keywords:
data augmentation, generative models, image classification, variational autoencodersAbstract
In the last decade, deep learning methods have become the key solution for various machine learning problems. One major drawback of deep learning methods is that they require large datasets to have a good generalization performance. Researchers propose data augmentation techniques for generating synthetic data to overcome this problem. Traditional methods, such as flipping, rotation etc., which are referred as transformation based methods in this study are commonly used for obtaining synthetic data in the literature. These methods take as input an image and process that image to obtain a new one. On the other hand, generative models such as generative adversarial networks, auto-encoders, after trained with a set of image learn to generate synthetic data. Recently generative models are commonly used for data augmentation in various domains. In this study, we evaluate the effectiveness of a generative model, variational autoencoders (VAE), on the image classification problem. For this purpose, we train a VAE using CIFAR-10 dataset and generate synthetic samples with this model. We evaluate the classification performance using various sized datasets and compare the classification performances on four datasets; dataset without augmentation, dataset augmented with VAE and two datasets augmented with transformation based methods. We observe that the contribution of data augmentation is sensitive to the size of the dataset and VAE augmentation is as effective as the transformation based augmentation methods.
Downloads
References
M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger and H. Greenspan, "Synthetic data augmentation using GAN for improved liver lesion classification," 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington.
Y. Xu, Y. Zhang, H.Wang and X. Liu, "Underwater image classification using deep convolutional neural networks and data augmentation," 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xiamen, 2017, pp. 1-5.
M. Zhang, Z. Cui, X. Wang and Z. Cao, "Data Augmentation Method of SAR Image Dataset," IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, 2018, pp. 5292-5295.
K. Chen, X. Zhou, Q. Zhou and H. Xu, "Adversarial Learning-based Data Augmentation for Rotation-robust Human Tracking," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, 2019, pp. 1942-1946
Shorten, C., Khoshgoftaar, T.M. A survey on Image Data Augmentation for Deep Learning. J Big Data 6, 60 (2019). https://doi.org/10.1186/s40537-019-0197-0
J. Shijie, W. Ping, J. Peiyi and H. Siping, "Research on data augmentation for image classification based on convolution neural networks," 2017 Chinese Automation Congress (CAC), Jinan, 2017, pp. 4165-4170.
C. Ge, I. Y. Gu, A. Store Jakola and J. Yang, "Cross-Modality Augmentation of Brain Mr Images Using a Novel Pairwise Generative Adversarial Network for Enhanced Glioma Classification," 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019, pp. 559-563.
A. H. Ornek and M. Ceylan, "Comparison of Traditional Transformations for Data Augmentation in Deep Learning of Medical Thermography," 2019 42nd International Conference on Telecommunications and Signal Processing (TSP), Budapest, Hungary, 2019, pp. 191-194.
Kingma, D.P., Welling, M. (2014). "Auto-Encoding Variational Bayes", CoRR, abs/1312.6114.
Jorge, J., Vieco, J., Paredes, R., Snchez, J., Bened, J. (2018). Empirical evaluation of variational autoencoders for data augmentation. VISIGRAPP.
Perez, L., Wang, J. (2017). The effectiveness of data augmentation in image classification using deep learning. CoRR, abs/1712.04621.
Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang, ‘Random Erasing Data Augmentation’. ArXiv e-prints 2017.
Terrance V, Graham WT. Improved regularization of convolutional neural networks with cutout. arXiv preprint. 2017.
Alex Krizhevsky, "Learning Multiple Layers of Features from Tiny Images", Technical Report, 2009.
Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geofrey E. (2017-05-24). "ImageNet classification with deep convolutional neural networks" (PDF). Communications of the ACM. 60 (6): 8490.
Y. Lecun, L. Bottou, Y. Bengio and P. Ha_ner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
J. Shijie, W. Ping, J. Peiyi and H. Siping, "Research on data augmentation for image classification based on convolution neural networks," 2017 Chinese Automation Congress (CAC), Jinan, 2017, pp. 4165-4170.
A. Merchant, T. Syed, B. Khan and R. Munir, "Appearance-based data augmentation for image datasets using contrast preserving sampling," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, 2018, pp. 1235-1240.
X. Liu et al., "Data Augmentation via Latent Space Interpolation for Image Classification," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, 2018, pp. 728-733.
E. D. Cubuk, B. Zoph, D. Mané, V. Vasudevan and Q. V. Le, "AutoAugment: Learning Augmentation Strategies From Data," 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 113-123.
R. Takahashi, T. Matsubara and K. Uehara, "Data Augmentation using Random Image Cropping and Patching for Deep CNNs," in IEEE Transactions on Circuits and Systems for Video Technology.
https://imgaug.readthedocs.io/, last accessed in June 12.
Downloads
Published
How to Cite
Issue
Section
License
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.