Abstract
With the advent of deep neural networks (DNNs) in the last two decades, tremendous developments have been made in many fields, such as image classification/recognition, voice recognition, and action recognition. These advanced DNNs require large amounts of labeled data, whose collection is costly and requires great effort. In this paper, we provide a convergence method for DNNs to solve some of these difficulties. First, we consider how to create labeled data using a generative adversarial network (GAN), one DNN method, and add additional networks to improve the quality of generated data. Then, we propose a convergence method for the DNNs and use a three-step evaluation to confirm this approach and show how to use the automatically generated data for training. With the method proposed in this paper, we hope that the manual work of labeling data can be reduced for many DNN applications.
Similar content being viewed by others
References
Hyochang A, Cho H-J (2019) Research of multi-object detection and tracking using machine learning based on knowledge for video surveillance system. Pers Ubiquit Comput:1–10
Zhao B, Feng J, Wu X, Yan S (2017) A survey on deep learning-based fine-grained object classification and semantic segmentation. Int J Autom Comput 14(2):119–135
Li D (2014) A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Trans Signal Inform Process 3
Gary HB, Jain V (2013) Deep and wide multiscale recursive networks for robust image labeling, arXiv preprint arXiv:1310.0354
Xuming H, Zemel RS, Carreira-Perpiñán MÁ (2004) Multiscale conditional random fields for image labeling, Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition, (CVPR 2004), Vol. 2
Goodfellow I et al (2014) Generative adversarial nets. Adv Neural Inf Proces Syst:2672–2680
Lee J, Park K (2019) GAN-based imbalanced data intrusion detection system. Pers Ubiquit Comput:1–8
Yi C, Cho J (2020) Improving the performance of multimedia pedestrian classification with images synthesized using a deep convolutional generative adversarial network. Multimed Tools Appl:1–16
Yu W, et al (2016) Visualizing and comparing AlexNet and VGG using deconvolutional layers. Proceedings of the 33 rd International Conference on Machine Learning
Yang J, et al (2008) Image super-resolution as sparse representation of raw image patches, 2008 IEEE conference on computer vision and pattern recognition. IEEE
Ledig C et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. Proc IEEE Conf Comput Vis Pattern Recognit:4681–4690
Kim J, Lee JK, Lee KM (2016) Deeply-recursive convolutional network for image super-resolution. Proc IEEE Conf Comput Vis Pattern Recognit:1637–1645
Johnson J, Alahi A, Li F-F (2016) Perceptual losses for real-time style transfer and super-resolution, European conference on computer vision. Springer, Cham, pp 694–711
González D et al (2019) A super-resolution enhancement of UAV images based on a convolutional neural network for mobile devices. Pers Ubiquit Comput:1–12
Goodfellow I (2016) NIPS 2016 Tutorial: Generative Adversarial Networks arXiv:1701.00160
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv preprint arXiv:1511.06434
Liu Y, Qin Z, Wan T, Luo Z (2018) Auto-painter: cartoon image generation from sketch by using conditional Wasserstein generative adversarial networks. Neurocomputing 311:78–87
DeepMind (2017) Producing flexible behaviours in simulated environments
Kadurin A, Nikolenko S, Khrabrov K, Aliper A, Zhavoronkov A (2017) druGAN: an advanced generative adversarial autoencoder model for de novo generation of new molecules with desired molecular properties in silico. Mol Pharmaceutics 14(9):3098–3104
Land EH (1977) The retinex theory of color vision. Sci Am 237(6):108–129
Wang S, Zheng J, Hu HM, Li B (2013) Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans Image Process 22(9):3538–3548
Guo X, Li Y, Ling H (2016) LIME: low-light image enhancement via illumination map estimation. IEEE Trans Image Process 26(2):982–993
Dong C, Loy CC, He K, Tang X (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778
Ignatov A, Kobyshev N, Timofte R, Vanhoey K, Gool LV (2017) Dslr-quality photos on mobile devices with deep convolutional networks, In Proceedings of the IEEE International Conference on Computer Vision, pp. 3277–3285
Park J, Lee JY, Yoo D, Kweon IS (2018) Distort-and-recover: color enhancement using deep reinforcement learning, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5928–5936
Chen YS, Wang YC, Kao MH, Chuang YY (2018) Deep photo enhancer: unpaired learning for image enhancement from photographs with gans, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6306–6314
Wei F et al (2018) A method for improving CNN-based image recognition using DCGAN. CMC Comput Mater Continua 57(1):167–178
Vanessa V, et al (2018) Evolving mario levels in the latent space of a deep convolutional generative adversarial network, Proceedings of the Genetic and Evolutionary Computation Conference, pp. 221–228
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection, IEEE computer society conference on computer vision and pattern recognition (CVPR'05)
Chollet F (2015) Keras
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yi, C., Cho, J. Convergence of multiple deep neural networks for classification with fewer labeled data. Pers Ubiquit Comput 27, 1055–1064 (2023). https://doi.org/10.1007/s00779-020-01448-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-020-01448-6