Abstract
Recently, Generative Adversarial Networks (GANs) have been widely applied for data augmentation given limited datasets. The state of the art is dominated by measures evaluating the quality of the generated images, that are typically all added to the training dataset. There is however no control of the generated data, in terms of the compromise between diversity and closeness to the original data, and this is our work’s focus. Our study concerns the prediction of soil moisture dissipation rates from synthetic aerial images using a CNN regressor. CNNs, however, require large datasets to successfully train them. To this end, we apply and compare two Generative Adversarial Networks (GANs) models: (1) Deep Convolutional Neural Network (DCGAN) and (2) Bidirectional Generative Adversarial Network (BiGAN), to generate fake images. We propose a novel approach that consists of studying which generated images to include into the augmented dataset. We consider a various number of images, selected for training according to their realistic character, based on the discriminator loss. The results show that, using our approach, the CNN trained on the augmented dataset generated by BiGAN and DCGAN allows a significant relative decrease of the Mean Absolute Error w.r.t the CNN trained on the original dataset. We believe that our approach can be generalized to any Generative Adversarial Network model.
The authors thank Campus France and Morocco CNRST for the financial support of this research, and Telecom SudParis, and Univ. Mohammed V during the different phases of this study. This work was also supported in part by the National Natural Science Foundation of China under Grant 61976030 and the funds for creative research groups of Chongqing Municipal Education Commission under Grant CXQT21034.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Papadavid, G., Hadjimitsis, D., Fedra, K., Michaelides, S.: Smart management and irrigation demand monitoring in Cyprus, using remote sensing and water resources simulation and optimization. Adv. Geosci. 30, 31–37 (2011)
Hassan-Esfahani, L., Torres-Rua, A., Jensen, A., Mckee, M.: Spatial root zone soil water content estimation in agricultural lands using Bayesian-based artificial neural networks and high resolution visual, NIR, and thermal imagery. Irrig. Drain. 66, 273–288 (2017)
Jha, K., Doshi, A., Patel, P.: Intelligent irrigation system using artificial intelligence and machine learning: a comprehensive review. Int. J. Adv. Res. 6(10), 1493–1502 (2018)
Abbas, A., Jain, S., Gour, M., Vankudothu, S.: Tomato plant disease detection using transfer learning with C-GAN synthetic images. Comput. Electron. Agric. 187, 106279 (2021)
Qin, H., El Yacoubi, M., Li, Y., Liu, C.: Multi-scale and multidirection GAN For CNN-based single palm-vein identification. IEEE Trans. Inf. Forensics Secur. 16, 2652–2666 (2021)
Gu, S., Bao, J., Chen, D., Wen, F.: GIQA: generated image quality assessment. arXiv preprint arXiv:2003.08932 (2020)
Borji, A.: Pros and cons of GAN evaluation measures. Comput. Vis. Image Underst. J. 179, 41–65 (2019)
Zhu, X., et al.: GAN-Based Image Super-Resolution with a Novel Quality Loss. Mathematical Problems in Engineering (2020)
Jean-François, P., Rhita, N.: Limitations of the SSIM quality metric in the context of diagnostic imaging. In: International Conference on Image Processing, ICIP 2015, pp. 2960–2963. IEEE, Canada (2015). https://doi.org/10.1109/ICIP.2015.7351345
Kovalenko, B.: Super resolution with Generative Adversarial Networks (n.d.)
Borji, A.: Pros and cons of GAN evaluation measures: new developments (2021). http://arxiv.org/abs/2103.09396
Shmelkov, K., Schmid, C., Alahari, K.: How good is my GAN? In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 218–234. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_14
Qin, Z., Liu, Z., Zhu, P., Xue, Y.: A GAN-based image synthesis method for skin lesion classification. Comput. Meth. Program. Biomed. 195, 0169–2607 (2020)
Zhao, Z., Zhang, Z., Chen, T., Singh, S., Zhang, H.: Image augmentations for GAN training (2020). http://arxiv.org/abs/2006.02595
Fawakherji, M., Ptena, C., Prevedello, I., Pretto, A., Bloisi, D.D., Nardi, D.: Data augmentation using GANs for crop/weed segmentation in precision farming. In: CCTA 2020 Conference, Montréal, pp. 279–284. IEEE Xplore (2020). https://doi.org/10.1109/CCTA41146.2020.9206297
Hammouch, H., El Yacoubi, M., Qin, H., Berrahou, A., Berbia, H., Chikhaoui, M.: A two-stage deep convolutional generative adversarial network-based data augmentation scheme for agriculture image regression tasks. In: International Conference on Cyber-physical Social Intelligence, CSI 2021, Beijing. IEEE Xplore (2021)
Goodfellow, I., Pouget-Abadie, J., Mirza, M.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning (2016). http://arxiv.org/abs/1605.09782
Cui, L., Tian, X., Shi, X., Wang, X., Cui, Y.: A semi-supervised fault diagnosis method based on improved bidirectional generative adversarial network. Appl. Sci. 11(20), 9401 (2021). https://doi.org/10.3390/app11209401
Tseng, D., et al.: Towards automating precision irrigation: deep learning to infer local soil moisture conditions from synthetic aerial agricultural images. In: CASE 2018 Conference, Munich, pp. 284–291. IEEE (2018). https://doi.org/10.1109/COASE.2018.8560431
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Hammouch, H., El-Yacoubi, M., Qin, H., Berbia, H., Chikhaoui, M. (2022). Controlling the Quality of GAN-Based Generated Images for Predictions Tasks. In: El Yacoubi, M., Granger, E., Yuen, P.C., Pal, U., Vincent, N. (eds) Pattern Recognition and Artificial Intelligence. ICPRAI 2022. Lecture Notes in Computer Science, vol 13363. Springer, Cham. https://doi.org/10.1007/978-3-031-09037-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-09037-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09036-3
Online ISBN: 978-3-031-09037-0
eBook Packages: Computer ScienceComputer Science (R0)