{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:48:52Z","timestamp":1778168932647,"version":"3.51.4"},"reference-count":33,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King Saud University, Riyadh, Saudi Arabia","award":["RSP2024R476"],"award-info":[{"award-number":["RSP2024R476"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Convolutional Neural Networks (CNNs) are a class of deep neural networks that have proven highly effective in areas such as image and video recognition. CNNs typically include several types of layers, such as convolutional layers, activation layers, pooling layers, and fully connected layers, all of which contribute to the network\u2019s ability to recognize patterns and features. The pooling layer, which often follows the convolutional layer, is crucial for reducing computational complexity by performing down-sampling while maintaining essential features. This layer\u2019s role in balancing the symmetry of information across the network is vital for optimal performance. However, the choice of pooling method is often based on intuition, which can lead to less accurate or efficient results. This research compares various standard pooling methods (MAX and AVERAGE pooling) on standard datasets (MNIST, CIFAR-10, and CIFAR-100) to determine the most effective approach in preserving detail, performance, and overall computational efficiency while maintaining the symmetry necessary for robust CNN performance.<\/jats:p>","DOI":"10.3390\/sym16111516","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T05:21:59Z","timestamp":1731388919000},"page":"1516","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Convolutional Neural Networks: A Comprehensive Evaluation and Benchmarking of Pooling Layer Variants"],"prefix":"10.3390","volume":"16","author":[{"given":"Afia","family":"Zafar","sequence":"first","affiliation":[{"name":"Department of Computer Science, National University of Technology, Islamabad 44000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0116-8453","authenticated-orcid":false,"given":"Noushin","family":"Saba","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Technology, Islamabad 44000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1842-8040","authenticated-orcid":false,"given":"Ali","family":"Arshad","sequence":"additional","affiliation":[{"name":"Department of Computing, NASTP Institute of Information Technology, Lahore 58810, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9750-3883","authenticated-orcid":false,"given":"Amerah","family":"Alabrah","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Science, King Saud University, Riyadh 11543, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5136-7927","authenticated-orcid":false,"given":"Saman","family":"Riaz","sequence":"additional","affiliation":[{"name":"Department of Computing, Riphah International University, Lahore 39101, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5064-1574","authenticated-orcid":false,"given":"Mohsin","family":"Suleman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Technology, Islamabad 44000, Pakistan"}]},{"given":"Shahneer","family":"Zafar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Technology, Islamabad 44000, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3566-7078","authenticated-orcid":false,"given":"Muhammad","family":"Nadeem","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Science and Technology, Beijing 100083, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","article-title":"A review of convolutional neural networks in computer vision","volume":"57","author":"Zhao","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s10462-023-10631-z","article-title":"Deep learning models for digital image processing: A review","volume":"57","author":"Archana","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Singh, S., Gupta, A., and Katiyar, K. (2023). Neural modeling and neural computation in a medical approach. Computational Techniques in Neuroscience, CRC Press.","DOI":"10.1201\/9781003398066-2"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Taye, M.M. (2023). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11.","DOI":"10.3390\/computation11030052"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"110229","DOI":"10.1016\/j.asoc.2023.110229","article-title":"Convolutional neural network pruning based on multi-objective feature map selection for image classification","volume":"139","author":"Jiang","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1016\/j.ajodo.2023.08.003","article-title":"Support vector machines","volume":"164","author":"Valkenborg","year":"2023","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"218","DOI":"10.21037\/atm.2016.03.37","article-title":"Introduction to machine learning: K-nearest neighbors","volume":"4","author":"Zhang","year":"2019","journal-title":"Ann. Transl. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/JPROC.2022.3153408","article-title":"A survey of deep learning on mobile devices: Applications, optimizations, challenges, and research opportunities","volume":"110","author":"Zhao","year":"2022","journal-title":"Proc. IEEE"},{"key":"ref_9","first-page":"21929","article-title":"Hybrid models for classifying histological images: An association of deep features by transfer learning with ensemble classifier","volume":"83","author":"Roberto","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"577","DOI":"10.18280\/ts.400216","article-title":"A new global pooling method for deep neural networks: Global average of top-k max-pooling","volume":"40","author":"Dogan","year":"2023","journal-title":"Trait. Du Signal"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"101070","DOI":"10.1016\/j.pecs.2022.101070","article-title":"Pool fire dynamics: Principles, models and recent advances","volume":"95","author":"Chen","year":"2023","journal-title":"Prog. Energy Combust. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1016\/j.neunet.2022.08.026","article-title":"Afinet: Attentive feature integration networks for image classification","volume":"155","author":"Pan","year":"2022","journal-title":"Neural Netw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhao, L., and Zhang, Z. (2024). A improved pooling method for convolutional neural networks. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-51258-6"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Krichen, M. (2023). Convolutional neural networks: A survey. Computers, 12.","DOI":"10.3390\/computers12080151"},{"key":"ref_15","unstructured":"Matoba, K., Dimitriadis, N., and Fleuret, F. (2024, September 15). Benefits of Max Pooling in Neural Networks: Theoretical and Experimental Evidence. In Transactions on Machine Learning Research; 2023. Available online: https:\/\/openreview.net\/forum?id=YgeXqrH7gA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1991","DOI":"10.1109\/TMM.2022.3141933","article-title":"A2SPPNet: Attentive atrous spatial pyramid pooling network for salient object detection","volume":"25","author":"Qiu","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103910","DOI":"10.1016\/j.imavis.2020.103910","article-title":"Recent advances in small object detection based on deep learning: A review","volume":"97","author":"Tong","year":"2020","journal-title":"Image Vis. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, J., Liang, Z., Tan, Z., Li, W., Li, Q., Ying, Z., Zhai, Y., He, Y., and Shen, Z. (2023). RVDNet: Rotated Vehicle Detection Network with Mixed Spatial Pyramid Pooling for Accurate Localization. International Conference on Artificial Intelligence and Communication Technology, Springer Nature.","DOI":"10.1007\/978-981-99-6956-2_27"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"119892","DOI":"10.1016\/j.eswa.2023.119892","article-title":"Avg-topk: A new pooling method for convolutional neural networks","volume":"223","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_20","unstructured":"Tang, T.N., Kim, K., and Sohn, K. (2023). Temporalmaxer: Maximize temporal context with only max pooling for temporal action localization. arXiv."},{"key":"ref_21","unstructured":"Bianchi, F.M., and Lachi, V. (2024). The expressive power of pooling in graph neural networks. Adv. Neural Inf. Process. Syst., 36."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9371","DOI":"10.1007\/s10586-018-2165-4","article-title":"Weighted pooling for image recognition of deep convolutional neural networks","volume":"22","author":"Zhu","year":"2019","journal-title":"Clust. Comput."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Stergiou, A., Poppe, R., and Kalliatakis, G. (2021, January 11\u201317). Refining activation downsampling with SoftPool. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01019"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.jspi.2022.11.001","article-title":"Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling","volume":"224","author":"Walter","year":"2023","journal-title":"J. Stat. Plan. Inference"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., and Wang, C. (2021, January 19\u201325). Learning the best pooling strategy for visual semantic embedding. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.irbm.2021.06.003","article-title":"A hybrid CNN-SVM threshold segmentation approach for tumor detection and classification of MRI brain images","volume":"43","author":"Khairandish","year":"2022","journal-title":"IRBM"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"111550","DOI":"10.1016\/j.knosys.2024.111550","article-title":"Multiview adaptive attention pooling for image\u2013text retrieval","volume":"291","author":"Ding","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1080\/23335777.2023.2177750","article-title":"Dual-path recommendation algorithm based on CNN and attention-enhanced LSTM","volume":"10","author":"Li","year":"2024","journal-title":"Cyber-Phys. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","article-title":"Dynamic neural networks: A survey","volume":"44","author":"Han","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","first-page":"7","article-title":"MNIST handwritten digit recognition with different CNN architectures","volume":"5","author":"Seng","year":"2021","journal-title":"J. Appl. Technol. Innov"},{"key":"ref_31","unstructured":"Giuste, F.O., and Vizcarra, J.C. (2020). Cifar-10 image classification using feature ensembles. arXiv."},{"key":"ref_32","unstructured":"Singla, S., Singla, S., and Feizi, S. (2021). Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3092","DOI":"10.1002\/sim.10114","article-title":"Standardization and other approaches to meta-analyze differences in means","volume":"43","author":"Hopkins","year":"2024","journal-title":"Stat. Med."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/11\/1516\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:30:40Z","timestamp":1760113840000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/16\/11\/1516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"references-count":33,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["sym16111516"],"URL":"https:\/\/doi.org\/10.3390\/sym16111516","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,12]]}}}