Download pdf
Comparative analysis of VGG, ResNet, and GoogLeNet architectures evaluating performance, computational efficiency, and convergence rates
- 1 Shanghai Jiaotong University
- 2 East China Normal University
- 3 Cambridge international school LITAI COLLEGE
* Author to whom correspondence should be addressed.
Abstract
This paper conducts an in-depth comparative analysis of three foundational machine learning architectures: VGG, ResNet, and GoogLeNet. The focus of the evaluation is their performance metrics on the CIFAR-100 dataset, a widely adopted benchmark in the field. Employing a comprehensive set of evaluation metrics, this investigation assesses not only testing accuracy but also the rate of training convergence and computational efficiency, providing a holistic perspective on the architectures' capabilities. Through rigorous experimentation, we elucidate the inherent advantages and drawbacks associated with each of these architectures. For instance, our findings delve into the nuances of how different architectures fare in terms of computational resources, which is vital for deployment in resource-constrained environments. Additionally, this study extends the analysis to explore the effect of hyperparameter settings, particularly learning rates, and the utility of data augmentation techniques in modulating the overall performance of each architecture. The ultimate objective is to furnish empirical insights that will assist researchers and practitioners in making well-informed choices when selecting a machine learning architecture for their specific application requirements.
Keywords
Machine Learning, Computer Vision, VGG Architecture, ResNet Architecture, GoogLeNet Architecture
[1]. Kim S, Jung D, Cho M. Relational Context Learning for Human-Object Interaction Detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 2925-2934.
[2]. Zhang Y, Peng C, Wang Q, et al. Unified Multi-Modal Image Synthesis for Missing Modality Imputation[J]. arXiv preprint arXiv:2304.05340, 2023.
[3]. Nielsen M, Wenderoth L, Sentker T, et al. Self-supervision for medical image classification: state-of-the-art performance with~ 100 labeled training samples per class[J]. arXiv preprint arXiv:2304.05163, 2023.
[4]. Jungo A, Doorenbos L, Da Col T, et al. Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery[J]. International journal of computer assisted radiology and surgery, 2023: 1-7.
[5]. Minarno, A. E., Bagas, S. Y., Yuda, M., Hanung, N. A., & Ibrahim, Z. (2022). Convolutional Neural Network featuring VGG-16 Model for Glioma Classification. JOIV: International Journal on Informatics Visualization, 6(3), 660-666.
[6]. Haque, M. F., Lim, H. Y., & Kang, D. S. (2019). Object detection based on VGG with ResNet network. In 2019 International Conference on Electronics, Information, and Communication (ICEIC) (pp. 1-3). IEEE.
[7]. Singla, A., Yuan, L., & Ebrahimi, T. (2016). Food/non-food image classification and food categorization using pre-trained googlenet model. In Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management (pp. 3-11).
[8]. Çınar, A., & Tuncer, S. A. (2021). Classification of lymphocytes, monocytes, eosinophils, and neutrophils on white blood cells using hybrid Alexnet-GoogleNet-SVM. SN Applied Sciences, 3, 1-11.
[9]. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[10]. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[11]. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.
Cite this article
Zhang,X.;Han,N.;Zhang,J. (2024). Comparative analysis of VGG, ResNet, and GoogLeNet architectures evaluating performance, computational efficiency, and convergence rates. Applied and Computational Engineering,44,172-181.
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 2023 International Conference on Machine Learning and Automation
© 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).