Abstract
Data augmentation is an effective technique for improving the accuracy of network. However, current data augmentation can not generate more diverse training data. In this article, we overcome this problem by proposing a novel form of data augmentation to fuse and fill different edge maps. The edge fusion augmentation pipeline consists of four parts. We first use the Sobel operator to extract the edge maps from the training images. Then a simple integrated strategy is used to integrate the edge maps extracted from different images. After that we use an edge fuse GAN (Generative Adversarial Network) to fuse the integrated edge maps to synthesize new edge maps. Finally, an edge filling GAN is used to fill the edge maps to generate new training images. This augmentation pipeline can augment data effectively by making full use of the features from training set. We verified our edge fusion augmentation pipeline on different datasets combining with different edge integrated strategies. Experimental results illustrate a superior performance of our pipeline comparing to the existing work. Moreover, as far as we know, we are the first using GAN to augment data by fusing and filling feature from multiple edge maps.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv preprint arXiv:1701.07875 (2017)
Bailo, O., Ham, D., Min Shin, Y.: Red blood cell image generation for data augmentation using conditional generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 0–0 (2019)
Bowles, C., et al.: GAN augmentation: Augmenting training data using generative adversarial networks. CoRR abs/1810.10863 (2018). http://arxiv.org/abs/1810.10863
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 113–123 (2019)
Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., Greenspan, H.: Gan-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing 321, 321–331 (2018)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5767–5777. Curran Associates, Inc. (2017). http://papers.nips.cc/paper/7159-improved-training-of-wasserstein-gans.pdf
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
He, K., Zhang, X., Ren, S., Jian, S.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)
Jackson, P.T., Atapour-Abarghouei, A., Bonner, S., Breckon, T., Obara, B.: Style augmentation: data augmentation via style randomization. arXiv preprint arXiv:1809.05375, pp. 1–13 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681–4690 (2017)
Lim, J.H., Ye, J.C.: Geometric GAN. arXiv preprint arXiv:1705.02894 (2017)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR abs/1411.1784 (2014). http://arxiv.org/abs/1411.1784
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. CoRR abs/1802.05957 (2018). http://arxiv.org/abs/1802.05957
Miyato, T., Koyama, M.: CGANs with projection discriminator. CoRR abs/1802.05637 (2018). http://arxiv.org/abs/1802.05637
Nazeri, K., Ng, E., Joseph, T., Qureshi, F.Z., Ebrahimi, M.: EdgeConnect: generative image inpainting with adversarial edge learning. arXiv Computer Vision and Pattern Recognition (2019)
Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2337–2346 (2019)
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536–2544 (2016)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Ren, R., Hung, T., Tan, K.C.: A generic deep-learning-based approach for automated surface inspection. IEEE Trans. Cybern. 48(3), 929–940 (2018)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Wang, X., You, M., Shen, C.: Adversarial generation of training examples for vehicle license plate recognition. CoRR abs/1707.03124 (2017). http://arxiv.org/abs/1707.03124
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR abs/1708.07747 (2017). http://arxiv.org/abs/1708.07747
Acknowledgement
This work was supported by National Key Research and Development Program of China (No. 2018YFB2101300), Shanghai Natural Science Foundation (Grant No. 18ZR1411400) and the National Trusted Embedded Software Engineering Technology Research Center (East China Normal University). We benefit a lot from the Research on algorithms for large-scale structural Optimization problems driven by Machine Learning [2019–2022, 19ZR141420].
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Xia, B., Zhang, Y., Chen, W., Wang, X., Wang, J. (2020). EdgeAugment: Data Augmentation by Fusing and Filling Edge Maps. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-61609-0_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61608-3
Online ISBN: 978-3-030-61609-0
eBook Packages: Computer ScienceComputer Science (R0)