Investigation of influence of additional convolutional and max-pooling layers in general adversarial network

Research Article
Open access

Investigation of influence of additional convolutional and max-pooling layers in general adversarial network

Zhibin Deng 1*
  • 1 College of Letter and Science, University of California, Santa Barbara, CA 93107, United States of America    
  • *corresponding author zhibin@ucsb.edu
ACE Vol.5
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-915371-57-7
ISBN (Online): 978-1-915371-58-4

Abstract

General Adversarial networks (GANs) are distinctively sensitive models to variation of parameters. Thus, a variable-control measurement is necessary to evaluate the performance of changing the parameters (layers) in GANs. This paper focuses on the performance of DCGANs. It reviews author’s experiment about the performance of DCGAN when applying the model to small datasets (MNIST, fashion- MNIST, cifar10, and human faces). This paper aims to discuss the influence of additional convolutional layers, max-pooling layers, and MLP in the generator and discriminator when dealing with small datasets. Using variable controlling, it is noteworthy that more convolutional layers can bring more accuracy for RGB images but not for single-channel images. MLP generators or discriminators are prone to model crashes. The respective analysis of each dataset’s result is provided later, which proposes that the layer’s influence is unstable among single-channel pictures. However, due to the complexity it brings, more layers can potentially increase the stability and convergence of RGB images. Some discussions for improving current experiments are listed, and some future research directions utilizing more advanced and matured methods are proposed.

Keywords:

DCGAN, CNN, Convolutional Layers, Max-pooling Layers, Image Generation.

Deng,Z. (2023). Investigation of influence of additional convolutional and max-pooling layers in general adversarial network . Applied and Computational Engineering,5,390-397.
Export citation

References

[1]. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative Adversarial Networks. Communications of the ACM, 63(11), pp.1–4. https://doi.org/10.1145/3422622

[2]. Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018). Generative Adversarial Networks: An overview. IEEE Signal Processing Magazine, 35(1), pp.1. https://doi.org/10.1109/msp.2017.2765202

[3]. Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET), pp.2-6. https://doi.org/10.1109/icengtechnol.2017.8308186

[4]. Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4681. https://doi.org/10.1109/cvpr.2017.19

[5]. Dong, H., Neekhara, P., Wu, C., & Guo, Y. (2017). Unsupervised Image-to-Image Translation with Generative Adversarial Networks. Arxiv, pp.1–4. https://doi.org/https://doi.org/10.48550/arXiv.1701.02676

[6]. Antipov, G., Baccouche, M., & Dugelay, J.-L. (2017). Face aging with conditional generative adversarial networks. 2017 IEEE International Conference on Image Processing (ICIP), pp.1. https://doi.org/10.1109/icip.2017.8296650

[7]. Weng, L. (2019). From GAN to WGAN. Arxiv, pp.5–11. https://doi.org/https://arxiv.org/abs/1904.08994

[8]. Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Arxiv, pp.1. https://doi.org/https://doi.org/10.48550/arXiv.1511.06434

[9]. Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. Arxiv, pp.2. https://doi.org/https://doi.org/10.48550/arXiv.1708.07747

[10]. Abouelnaga, Y., Ali, O. S., Rady, H., & Moustafa, M. (2016). CIFAR-10: Knn-based ensemble of classifiers. 2016 International Conference on Computational Science and Computational Intelligence (CSCI), pp.1. https://doi.org/10.1109/csci.2016.0225

[11]. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., … Zheng, X. (2016, November). {tensorflow}: A system for {large-scale} machine learning. USENIX. Retrieved September 19, 2022, from https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi

[12]. Imambi, S., Prakash, K. B., & Kanagachidambaresan, G. R. (2021, January 23). Pytorch. SpringerLink. Retrieved September 19, 2022, from https://link.springer.com/chapter/10.1007/978-3-030-57077-4_10

[13]. Liu, M.-Y., Huang, X., Yu, J., Wang, T.-C., & Mallya, A. (2021). Generative adversarial networks for image and video synthesis: Algorithms and applications. Proceedings of the IEEE, 109(5), pp.839. https://doi.org/10.1109/jproc.2021.3049196

[14]. Karras, T., Laine, S., & Aila, T. (2019). A Style-Based Generator Architecture for Generative Adversarial Networks. CVPR 2019 Open Access, pp.4401.

[15]. Mao, X., Li, Q., Xie, H., Lau, R. Y. K., Wang, Z., & Smolley, S. P. (2017). Least Squares Generative Adversarial Networks. ICCV 2017 Open Access, pp.2794.

Cite this article

Deng,Z. (2023). Investigation of influence of additional convolutional and max-pooling layers in general adversarial network . Applied and Computational Engineering,5,390-397.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 3rd International Conference on Signal Processing and Machine Learning

ISBN：978-1-915371-57-7(Print) / 978-1-915371-58-4(Online)
Editor：Omer Burak Istanbullu
Conference website: http://www.confspml.org
Conference date: 25 February 2023
Series: Applied and Computational Engineering
Volume number: Vol.5
ISSN：2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative Adversarial Networks. Communications of the ACM, 63(11), pp.1–4. https://doi.org/10.1145/3422622

[2]. Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018). Generative Adversarial Networks: An overview. IEEE Signal Processing Magazine, 35(1), pp.1. https://doi.org/10.1109/msp.2017.2765202

[3]. Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 International Conference on Engineering and Technology (ICET), pp.2-6. https://doi.org/10.1109/icengtechnol.2017.8308186

[4]. Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4681. https://doi.org/10.1109/cvpr.2017.19

[5]. Dong, H., Neekhara, P., Wu, C., & Guo, Y. (2017). Unsupervised Image-to-Image Translation with Generative Adversarial Networks. Arxiv, pp.1–4. https://doi.org/https://doi.org/10.48550/arXiv.1701.02676

[6]. Antipov, G., Baccouche, M., & Dugelay, J.-L. (2017). Face aging with conditional generative adversarial networks. 2017 IEEE International Conference on Image Processing (ICIP), pp.1. https://doi.org/10.1109/icip.2017.8296650

[7]. Weng, L. (2019). From GAN to WGAN. Arxiv, pp.5–11. https://doi.org/https://arxiv.org/abs/1904.08994

[8]. Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Arxiv, pp.1. https://doi.org/https://doi.org/10.48550/arXiv.1511.06434

[9]. Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. Arxiv, pp.2. https://doi.org/https://doi.org/10.48550/arXiv.1708.07747

[10]. Abouelnaga, Y., Ali, O. S., Rady, H., & Moustafa, M. (2016). CIFAR-10: Knn-based ensemble of classifiers. 2016 International Conference on Computational Science and Computational Intelligence (CSCI), pp.1. https://doi.org/10.1109/csci.2016.0225

[11]. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., … Zheng, X. (2016, November). {tensorflow}: A system for {large-scale} machine learning. USENIX. Retrieved September 19, 2022, from https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi

[12]. Imambi, S., Prakash, K. B., & Kanagachidambaresan, G. R. (2021, January 23). Pytorch. SpringerLink. Retrieved September 19, 2022, from https://link.springer.com/chapter/10.1007/978-3-030-57077-4_10

[13]. Liu, M.-Y., Huang, X., Yu, J., Wang, T.-C., & Mallya, A. (2021). Generative adversarial networks for image and video synthesis: Algorithms and applications. Proceedings of the IEEE, 109(5), pp.839. https://doi.org/10.1109/jproc.2021.3049196

[14]. Karras, T., Laine, S., & Aila, T. (2019). A Style-Based Generator Architecture for Generative Adversarial Networks. CVPR 2019 Open Access, pp.4401.

[15]. Mao, X., Li, Q., Xie, H., Lau, R. Y. K., Wang, Z., & Smolley, S. P. (2017). Least Squares Generative Adversarial Networks. ICCV 2017 Open Access, pp.2794.

For authors
Guide for authors Policies for authors Aims and scope Subscription Open access policy
For editors
Policies for editors Editorial board
For reviewers
Policies for reviewers Privacy policy

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.