Convolutional Neural Networks: A Survey
Open accessThe DOI matches its Crossref record; 199 of the 199 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI) has become a cornerstone of modern technology, revolutionizing industries from healthcare to finance. Convolutional neural networks (CNNs) are a subset of AI that have emerged as a powerful tool for various tasks including image recognition, speech recognition, natural language processing (NLP), and even in the field of genomics, where they have been utilized to classify DNA sequences. This paper provides a comprehensive overview of CNNs and their applications in image recognition tasks. It first introduces the fundamentals of CNNs, including the layers of CNNs, convolution operation (Conv_Op), Feat_Maps, activation functions (Activ_Func), and training methods. It then discusses several popular CNN architectures such as LeNet, AlexNet, VGG, ResNet, and InceptionNet, and compares their performance. It also examines when to use CNNs, their advantages and limitations, and provides recommendations for developers and data scientists, including preprocessing the data, choosing appropriate hyperparameters (Hyper_Param), and evaluating model performance. It further explores the existing platforms and libraries for CNNs such as TensorFlow, Keras, PyTorch, Caffe, and MXNet, and compares their features and functionalities. Moreover, it estimates the cost of using CNNs and discusses potential cost-saving strategies. Finally, it reviews recent developments in CNNs, including attention mechanisms, capsule networks, transfer learning, adversarial training, quantization and compression, and enhancing the reliability and efficiency of CNNs through formal methods. The paper is concluded by summarizing the key takeaways and discussing the future directions of CNN research and development.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Finally, RobotReviewer/RobotSearch employs an ensemble classifier, combining multiple CNN models (Krichen 2023) and soft-margin Support Vector Machines (Boser et al. 1992) in order to categorise articles based on their risk of bias assessment (either low or high/unclear) and concurrently extract sentences that substantiate these judgements.”
From Artificial intelligence for literature reviews: opportunities and challenges (2024) · cites this paper as Krichen 2023
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273 · cited 1×
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
Understanding of a convolutional neural network
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017) · 2017 International Conference on Engineering and Technology (ICET) · doi:10.1109/icengtechnol.2017.8308186 · Cited by 3,986 · cited 1×
“Convolutional neural networks (CNNs) [14–16] are a popular type of ML model that have been widely utilized for various tasks, including image recognition [17–20], speech recognition [21–25], and NLP [26–30].”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503
Chen, Y., Jiang, H., Li, C., Jia, X., & Ghamisi, P. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2584107 · Cited by 2,984
Artificial intelligence and the future of work: Human-AI symbiosis in organizational decision making
Jarrahi, M. H. (2018) · Business Horizons · doi:10.1016/j.bushor.2018.03.007 · Cited by 2,772
Duan, Y., Edwards, J. S., & Dwivedi, Y. K. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2019.01.021 · Cited by 2,628
Attention mechanisms in computer vision: A survey
Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0271-y · Cited by 2,566 · cited 1×
“Attention mechanisms are a powerful tool for improving the performance of CNNs [178–182].”
Research works printed but not linked: 9
- Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
- Bengio, Y., Goodfellow, I., and Courville, A. (2017). Deep Learning, MIT Press.
- Gan, 2019, Research of facial beauty prediction based on deep convolutional features using double activation layer, Acta Electonica Sin., 47, 636
- Simon, 2019, Shallow cnn with lstm layer for tuberculosis detection in microscopic images, Int. J. Recent Technol. Eng., 7, 56
- Ndong, P.S.B., Adoni, W.Y.H., Nahhal, T., Kimpolo, C., Krichen, M., Byed, A.E., Assayad, I., and Mutombo, F.K. (2021). Advances on Smart and Soft Computing: Proceedings of ICACIn 2021, Springer.
- Mehdi, C.A., Nour-Eddine, J., and Mohamed, E. (2022, January 22–27). Regularization in CNN: A Mathematical Study for L 1, L 2 and Dropout Regularizers. Proceedings of the International Conference on Advanced Intelligent Systems for Sustainable Development, Rabat, Morocco. · DOI
- Moolayil, J., Moolayil, J., and John, S. (2019). Learn Keras for Deep Neural Networks, Springer. · DOI
- Wu, P. (2021-, January 27). PyTorch 2.0: The Journey to Bringing Compiler Technologies to the Core of PyTorch (Keynote). Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization, Virtual.
- Rundong, 2022, Multidimensional Linear Data Processing Based on OpenCL Kernel Function in MXNet Framework, Front. Data Domputing, 4, 29
Cited by
Items 101–200 of 869
Alfred, R., Leo, J., & Kaijage, S. F. (2024) · Smart Agricultural Technology · doi:10.1016/j.atech.2024.100726 · Cited by 23
Zheng, Y., Shcherbakova, G. Y., Rusyn, B., Sachenko, A., Volkova, N. P., Kliushnikov, I. M., & Antoshchuk, S. G. (2025) · Sustainability · doi:10.3390/su17030927 · Cited by 23
Alatefi, S., Agwu, O. E., Amar, M. N., & Djema, H. (2025) · Fuel · doi:10.1016/j.fuel.2025.135073 · Cited by 23
An Overview of CNN-Based Image Analysis in Solar Cells, Photovoltaic Modules, and Power Plants
Matusz-Kalász, D., Bodnár, I., & Jobbágy, M. (2025) · Applied Sciences · doi:10.3390/app15105511 · Cited by 23
Andriani, S., Galantucci, S., Iannacone, A., Maci, A., & Pirlo, G. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104507 · Cited by 22
Maize Disease Classification System Design Based on Improved ConvNeXt
Li, H., Qi, M., Du, B., Li, Q., Gao, H., Yu, J., Bi, C., Yu, H., Liang, M., Ye, G., et al. (2023) · Sustainability · doi:10.3390/su152014858 · Cited by 22
A Full-Scale Connected CNN–Transformer Network for Remote Sensing Image Change Detection
Chen, M., Zhang, Q., Ge, X., Xu, B., Hu, H., Zhu, Q., & Zhang, X. (2023) · Remote Sensing · doi:10.3390/rs15225383 · Cited by 22
“CNNs possess strong capability for pixel-level feature extraction, such as Unet [14] and ResNet [15], the most representative semantic segmentation networks [16,17].”
MethodZhao, X., Ren, F., Sun, H., & Qi, Q. (2024) · Electronics · doi:10.3390/electronics13030490 · Cited by 22
Transforming oral cancer care: The promise of deep learning in diagnosis
Varalakshmi, D., Tharaheswari, M., Anand, T., & Saravanan, K. M. (2024) · Oral Oncology Reports · doi:10.1016/j.oor.2024.100482 · Cited by 22
A Novel Deep Learning Approach for Myocardial Infarction Detection and Multi-Label Classification
Abbas, S., Ojo, S., Krichen, M., Alamro, M. A., Mihoub, A., & Vilčeková, L. (2024) · IEEE Access · doi:10.1109/access.2024.3401744 · Cited by 22
“CNNs and conventional ANNs are similar in that both are made up of neurons that learn to optimize themselves [38].”
BackgroundSelf-citationKitaya, K., Yasuo, T., & Yamaguchi, T. (2024) · Medicina · doi:10.3390/medicina60060972 · Cited by 22
“Nonlinear activation functions are used for the outputs of convolution operations The representative nonlinear activation function adopted in CNN models is the ramp function (rectified linear unit, ReLU), defined as f(x) = max (0, x), where x is the input to a neuron [75].”
MethodThe Research on Video Analysis of Key Motion Positions Based on Deep Learning Technology
Wang, Z., Cheng, H., & Qin, Q. (2025) · International Journal of e-Collaboration · doi:10.4018/ijec.373713 · Cited by 21
“The introduction of pooling layers further enhances the model's ability to generalize by down-sampling feature maps, thereby reducing dimensionality while retaining essential information (Anand et al., 2023; Krichen, 2023).”
Jun, K., Lee, K.-J., Lee, S., Lee, H. H., & Kim, M. S. (2023) · Bioengineering · doi:10.3390/bioengineering10101133 · Cited by 21
“…a joint In contrast, a GCN is particularly well suited for tasks such as node classi fi cation and link prediction within data structured as graphs [35]. node v ti can be formulated as the following equation: Examples of such data encompass social networks, chemical molecules, and skeletal…”
BackgroundMethodYang, H., & Li, Z. (2024) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi13020034 · Cited by 21
“Some of the earliest attempts have used CNN (Convolutional Neural Network) models [43–45] to capture the spatial characteristics of traffic flow.”
BackgroundMijwil, M. M., Esen, A., & Shamil, A. (2023) · Babylonian Journal of Machine Learning · doi:10.58496/bjml/2023/008 · Cited by 21
“Neural networks can be broadly categorised into different types based on their architecture and functionality, such as feedforward neural networks [11], recurrent neural networks (RNNs)[12], convolutional neural networks (CNNs)[13][14], and more.”
BackgroundGuo, S., Yang, X., Farizan, N. H., & Samsudin, S. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e36067 · Cited by 22
“Given the diverse learning demands of students and the complexity of dance skills, the introduction of Convolutional Neural Networks (CNNs) in deep learning offers a powerful solution [7 – 9].”
BackgroundRetractedDeep Learning for Automatic Detection of Volcanic and Earthquake-Related InSAR Deformation
Liu, X., Zhang, Y., Shan, X., Wang, Z., Gong, W., & Zhang, G. (2025) · Remote Sensing · doi:10.3390/rs17040686 · Cited by 21
A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future TrendsPreprint
Younesi, A., Ansari, M., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.48550/arxiv.2402.15490 · Cited by 21
Transformer in UAV Image-Based Weed Mapping
Zhao, J., Berge, T. W., & Geipel, J. (2023) · Remote Sensing · doi:10.3390/rs15215165 · Cited by 20
Abdalzaher, M. S., Krichen, M., & Fouda, M. M. (2024) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2024.102925 · Cited by 20
Self-citationSeeing the Sound: Multilingual Lip Sync for Real-Time Face-to-Face Translation
Oskooei, A. R., Aktaş, M. S., & Keleş, M. (2024) · Computers · doi:10.3390/computers14010007 · Cited by 20
Vaziri, A., Moghaddam, P. S., Shoeibi, M., & Kaveh, M. (2025) · Future Internet · doi:10.3390/fi17040169 · Cited by 20
“Instead of traditional fully connected layers, CNNs utilize local connectivity and weight sharing to drastically reduce the number of parameters, making them more efficient in handling large-scale image datasets [51–54].”
Artificial intelligence in sustainable organic waste treatment: a review
Sugumaran, D., Dananjaya, U. M., Kodippili, S. P., Alwis, M. M. D., Attigala, D. L., Ranasinghe, N. N., Manatunga, D. C., Dassanayake, R. S., Zhou, Y., & Liu, Y. (2025) · Waste Disposal & Sustainable Energy · doi:10.1007/s42768-025-00246-1 · Cited by 19
Convolutional Neural Networks for Raw Signal Classification in CNC Turning Process Monitoring
Stathatos, E., Tzimas, E., Benardos, P., & Vosniakos, G.-C. (2024) · Sensors · doi:10.3390/s24051390 · Cited by 19
“CNNs operate by extracting local information from the input arrays in the form of feature maps [20,23].”
BackgroundA Review on Deep Learning For Electroencephalogram Signal Classification
Gatfan, S. K. (2024) · Journal of Al-Qadisiyah for Computer Science and Mathematics · doi:10.29304/jqcsm.2024.16.11453 · Cited by 19
Shaikh, M. S., Dong, X., Zheng, G., Wang, C., & Lin, Y. (2024) · Mathematics · doi:10.3390/math12111620 · Cited by 19
Kim, T. H., Krichen, M., Ojo, S., Alamro, M. A., & Sampedro, G. A. (2024) · Diagnostics · doi:10.3390/diagnostics14111174 · Cited by 19
“The segmentation model consists of a convolutional neural network (CNN) encoder-decoder architecture that is commonly used for image segmentation where the model itself learns to assign labels to each pixel in the input image [24].”
MethodSelf-citationApplications of Machine Learning Technologies for Feedstock Yield Estimation of Ethanol Production
Lim, H., & Kim, S. (2024) · Energies · doi:10.3390/en17205191 · Cited by 19
Dehbozorgi, P., Duponchel, L., Motto‐Ros, V., & Bocklitz, T. W. (2025) · Analysis & Sensing · doi:10.1002/anse.202500106 · Cited by 18
Classification of rice plant diseases using efficient DenseNet121
Ismail, A., Hamdy, W., Ibrahim, A. H., & Awad, W. A. (2026) · Scientific Reports · doi:10.1038/s41598-026-38078-6 · Cited by 18
“Nevertheless, implementing these models in actual agricultural environments has a distinct set of difficulties 16 .”
From Traditional Methods to 3D U-Net: A Comprehensive Review of Brain Tumour Segmentation Techniques
Saleh, M. M., Salih, M. E., Ahmed, M. A. A., & Hussein, A. M. (2025) · Journal of Biomedical Science and Engineering · doi:10.4236/jbise.2025.181001 · Cited by 18
Ravi Raj, K. G., & Demirkol, I. (2025) · Scientific Reports · doi:10.1038/s41598-025-22835-0 · Cited by 17
“CNNs are made to autonomously recognize and identify features from pictures that might be used to predict the emotions of a person based on the picture 49,50 .”
Mental illness detection through harvesting social media: a comprehensive literature review
Shah, S. M., Aljawarneh, M. M., Saleem, M. A., & Jawarneh, M. S. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2296 · Cited by 17
Ding, W., Li, H., Chew, C., Zhang, X., & Huang, H. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.120471 · Cited by 17
Surrogate modeling for flow simulations using design variable-coded deep learning networks
Matai, R. (2025) · Journal of Engineering and Applied Science · doi:10.1186/s44147-025-00634-8 · Cited by 17
Review of Masked Face Recognition Based on Deep Learning
Saoud, B., Mohamed, A. H. H. M., Shayea, I. A. M., El‐Saleh, A. A., & Alashbi, A. A. (2025) · Technologies · doi:10.3390/technologies13070310 · Cited by 17
Borra, S. R., Yukthika, M., Bhargavi, M., Samskruthi, M., Saisri, P. V., Akhila, Y., & Sooram, A. (2023) · e-Prime - Advances in Electrical Engineering Electronics and Energy · doi:10.1016/j.prime.2023.100415 · Cited by 17
Sun, P., Yang, C., Zhou, X., & Wang, W. (2023) · Sensors · doi:10.3390/s23218864 · Cited by 16
Pclf: Parallel cnn-lstm fusion model for sms spam filtering
Derakhshi, M. R. F., Zafarani-Moattar, E., Alkaabi, H. A., & Almarashy, A. H. J. (2024) · BIO Web of Conferences · doi:10.1051/bioconf/20249700136 · Cited by 16
“…stage, we employ the fully connected layer as a classifier Because of its efficiency in separating the fused features that are passed through it [29], which learns the relationships between the features to identify the message according to the label to spam and non-spam. the PCLF algorithm is…”
MethodAI-Driven Process Optimization Framework for Enhancing Print Quality in Aerosol Jet Printing
Zhang, H., Kim, Y., Cui, L., Moon, S. K., & Choi, J. P. (2025) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-025-00721-4 · Cited by 16
“To achieve competitive performance, a lightweight CNN architecture is employed for in-situ monitoring of the AJP process [49, 50].”
Vocal performance evaluation of the intelligent note recognition method based on deep learning
Chang, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-99357-2 · Cited by 16
Detecting deception: employing deep neural networks for fraudulent review detection on Amazon
Jayasinghe, J. M. T., & Dassanayaka, S. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11485-y · Cited by 17
“The final layer uses loss functions that relate to specific categories, and the strategies developed for optimizing traditional NNs, such as gradient descent and back-propagation, are also applicable to CNNs [50, 51].”
García, J. A. G., Lazzeri, G., & Tapete, D. (2025) · Remote Sensing · doi:10.3390/rs17173126 · Cited by 16
Multi-Branch Network for Color Image Denoising Using Dilated Convolution and Attention Mechanisms
Duong, M.-T., Thi, B.-T. N., Lee, S., & Hong, M.-C. (2024) · Sensors · doi:10.3390/s24113608 · Cited by 16
“Currently, owing to the tremendous success of deep-learning-based approaches in image recognition and classification tasks [5], many scientists have begun developing deep-learning-based methods for image denoising [6,7].”
BackgroundMethodAccelerating Native Inference Model Performance in Edge Devices using TensorRT
Gopikrishna, P. B., Rubell Marion Lincy, G., Rishekeeshan, A., & Deekshitha (2024) · IEEE Recent Advances in Intelligent Computational Systems · doi:10.1109/raics61201.2024.10690032 · Cited by 15
Bidirectional Mamba with Dual-Branch Feature Extraction for Hyperspectral Image Classification
Sun, M. Y., Zhang, J., He, X., & Zhong, Y. (2024) · Sensors · doi:10.3390/s24216899 · Cited by 15
Wheat growth stage identification method based on multimodal data
Li, Y., Che, Y., Zhang, H., Zhang, S., Zheng, L., Ma, X., Xi, L., & Xiong, S. (2024) · European Journal of Agronomy · doi:10.1016/j.eja.2024.127423 · Cited by 15
Zhu, L., Li, M., Wu, X., Xu, S., Guo, Y., & Jiang, L. (2025) · Journal of Analytical and Applied Pyrolysis · doi:10.1016/j.jaap.2025.107465 · Cited by 15
Sapitang, M., Dullah, H., Latif, S. D., Ng, J. L., Huang, Y. F., Malek, M. B. A., El‐Shafie, A., & Ahmed, A. N. (2024) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2024.101236 · Cited by 14
Machine Learning Methods from Shallow Learning to Deep Learning
Akıncı, T. Ç., Topsakal, O., & Akbaş, M. İ. (2024) · The Springer series in applied machine learning · doi:10.1007/978-3-031-69499-8_1 · Cited by 14
Automated Cough Analysis with Convolutional Recurrent Neural Network
Wang, Y., Wahab, M., Hong, T., Molinari, K., Gauvreau, G. M., Cusack, R. P., Gao, Z., Satia, I., & Fang, Q. (2024) · Bioengineering · doi:10.3390/bioengineering11111105 · Cited by 14
“More recently, convolutional recurrent neural networks (CRNNs) have emerged as a powerful technique for time-series data analysis, such as recorded audio data [25].”
Oviesi, S., Tarokh, M. J., & Momeni, M. K. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06740-3 · Cited by 14
“[18, 19].”
Exploring optimizer efficiency for facial expression recognition with convolutional neural networks
Madni, S. H. H., Pathmanatan, L. A. L., Faheem, M., Shehzad, H. M. F., & Shah, S. (2025) · The Journal of Engineering · doi:10.1049/tje2.70060 · Cited by 14
MUST: Multi-channel ultrasonic spectrogram transformer for microdamage detection in metals
Ma, B., Chen, L., Sun, X., Yang, X., & Kong, Q. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112680 · Cited by 14
Are vision transformers replacing convolutional neural networks in scene interpretation?: A review
Rosy, N. A., Balasubadra, K., & Deepa, K. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07574-1 · Cited by 14
“From an extensive survey, it is observed that most of the neural network-based scene interpretation models are computationally costly to model and need vast storage space [6].”
Advances in Machine Learning for Structural Seismic Response Prediction: A Comprehensive Review
Noor, U. A. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10395-5 · Cited by 14
Junaid, M., Aliev, H., Park, S., Kim, H., Yoo, H., & Sim, S. (2024) · Sensors · doi:10.3390/s24072145 · Cited by 14
Lim, J., Luo, C., Lee, S., Song, Y. E., & Jung, H. (2024) · Sensors · doi:10.3390/s24082595 · Cited by 14
“Recent studies have been exploring the application of conventional CNN-based methodologies to vision-based action recognition using extracted skeletons [22–27].”
BackgroundLate feature fusion using neural network with voting classifier for Parkinson’s disease detection
Aljohani, A. A. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02683-0 · Cited by 14
Islam, N., Hasib, K. M., Joti, F. A., Karim, A., & Azam, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.17051 · Cited by 14
“While convolutional layers effectively extract useful features from the input image, the pooling layer downsamples the spatial dimensions of the feature map, conserving the important features and enhancing computational efficiency [7].”
Aerosol Optical Depth Retrieval for Sentinel-2 Based on Convolutional Neural Network Method
Jiang, J., Liu, J., & Jiao, D. (2023) · Atmosphere · doi:10.3390/atmos14091400 · Cited by 13
Power System Transient Stability Assessment Using Convolutional Neural Network and Saliency Map
Lee, H., Kim, J., Park, J. H., & Chung, S. (2023) · Energies · doi:10.3390/en16237743 · Cited by 13
Decision-Making Model for Life Cycle Management of Aircraft Components
Kabashkin, I., & Susanin, V. (2024) · Mathematics · doi:10.3390/math12223549 · Cited by 13
Laser ultrasonic inspection of surface and subsurface defects in materials based on deep learning
Zhang, J., Wan, H., Sun, F., Chen, X., Jia, K., Li, F., Cheng, L., Xu, X., Yan, X., Yuan, P., et al. (2024) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2024.2429691 · Cited by 13
“After multiple convolution and pooling operations, the extracted high-dimensional features are input to the fully connected layer for the final classification or regression output [36,37].”
A review on magnetic-assisted localization for mobile robots
Lei, W., Zhang, C., Jin, Z., & Chen, J. (2025) · Measurement · doi:10.1016/j.measurement.2025.116643 · Cited by 13
Research advancements in machine learning-assisted design of reinforced composite radiation shields
Okonkwo, U. C., Okafor, C. E., Ahmad, S., Ohagwu, C. C., Aronu, M. E., Okokpujie, I. P., Idumah, C. I., Chukwu, N. N., Chukwunyelu, C. E., & Mustafa, J. (2025) · Life Cycle Reliability and Safety Engineering · doi:10.1007/s41872-025-00313-w · Cited by 13
Spatial and Spectral Structure-Aware Mamba Network for Hyperspectral Image Classification
Zhang, J., Sun, M. Y., & Chang, S. (2025) · Remote Sensing · doi:10.3390/rs17142489 · Cited by 13
Geng, J., Deng, J., Bai, Z., Wen, X., Lu, J., Yan, Q., & Yang, X. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106687 · Cited by 13
Ilo, B., Badjona, A., Singh, Y., Shenfield, A., & Zhang, H. (2025) · Processes · doi:10.3390/pr13113731 · Cited by 13
Li, N., Wang, Z., Huang, Y., Tian, J., Li, X., & Xiao, Z. (2024) · Sensors · doi:10.3390/s24123758 · Cited by 13
“Although Convolutional Neural Networks (CNNs) are widely used in object detection [3,4], there are still some challenges in applying CNNs to scene text detection due to issues such as the varying sizes and orientations of text [5].”
BackgroundCustomized Convolutional Neural Network for Glaucoma Detection in Retinal Fundus Images
Islami, F., Sumijan, S., & Defit, S. (2024) · Jurnal Penelitian Pendidikan IPA · doi:10.29303/jppipa.v10i8.7614 · Cited by 13
A real-time environmental translator for emotion recognition in autism spectrum disorder
Levy, L., Ambaw, A., Ben‐Itzchak, E., & Holdengreber, E. (2024) · Scientific Reports · doi:10.1038/s41598-024-83229-2 · Cited by 13
Toward Flare-Free Images: A SurveyPreprint
Kotp, Y., & Torki, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.14354 · Cited by 13
“A. Overview of Deep Neural Networks Architectures 1) Convolutional Neural Network : Convolutional Neural Networks (CNNs) [46, 47, 48, 49, 50] stand as one of the most successful and widely adopted architectures within the realm of deep learning, particularly in the field of computer vision.”
BackgroundYu, W., Jang, J.-C. C., Zhu, Y., Peng, J., Yang, W., & Li, K. (2024) · Sustainability · doi:10.3390/su16146088 · Cited by 12
Pan, Q., Zheng, S.-C., & Liu, X.-J. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112458 · Cited by 12
Kohler, M., Mitsios, D., & Endisch, C. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.12.005 · Cited by 12
Performance comparison of deep learning models for MRI-based brain tumor detection
Alsufyani, A. (2025) · AIMS bioengineering · doi:10.3934/bioeng.2025001 · Cited by 12
Hawana, A., Hassan, E. S., El‐Shafai, W., & El‐Dolil, S. A. (2025) · Security and Privacy · doi:10.1002/spy2.70000 · Cited by 12
Si, Q., & Han, S. I. (2025) · IEEE Access · doi:10.1109/access.2025.3544631 · Cited by 12
“Convolutional Neural Networks (CNN) are extensively used in computer vision [11], and have become the predominant algorithm for image classification [12].”
Añez, D., Conti, G., Uriarte, J. J., Olmedo, J. J. S., Martínez‐Murillo, R., & Casanova-Carvajal, Ó. (2025) · Medicina · doi:10.3390/medicina61122237 · Cited by 12
“Convolutional neural networks (CNNs) [4] are among the most widely used deep-learning architectures in breast cancer imaging.”
Deep learning for epileptic seizure prediction from EEG signals: A review
Huang, X., Meng, H., & Li, Z. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109518 · Cited by 12
HGCNN-LSTM: A Data-driven Approach for Cyberattack Detection in Cyber-Physical Systems
Abinash, S., Srivatsan, N., Hemachandran, S. K., & Priyanga, S. (2025) · SN Computer Science · doi:10.1007/s42979-024-03613-7 · Cited by 12
“The proposed framework is a DL approach that integrates CNN [22], LSTM [23], and Hyper-graphs [24, 25 ] to precisely analyse the CPS data and detect cyber-attacks on ICS.”
Miao, H., Zhang, R., Song, Z., & Chang, Q. (2025) · Remote Sensing · doi:10.3390/rs17030406 · Cited by 12
Bolat, Y., Murray, I. D., Ren, Y., & Ferdosian, N. (2025) · Sensors · doi:10.3390/s25154595 · Cited by 12
“Additionally, convolutional blocks, each consisting of convolutional and pooling layers, demand substantial computational resources, and their workloads are not evenly balanced [48].”
Deep learning for economic transformation: a parametric review
Tariq, U., Ahmed, I., Khan, M. A., & Bashir, A. K. (2024) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v35.i1.pp520-541 · Cited by 11
Keerthinathan, P., Narmilan, A., Kelly, J. E., Mandel, N., Dehaan, R., Zheng, L., Hamilton, G. S., & Gonzalez, F. (2024) · Remote Sensing · doi:10.3390/rs16132363 · Cited by 11
Shen, Z., Liu, W. N., & Xu, S. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3496725 · Cited by 11
“CNN is capable of extracting image features through convolutional operations, but has limitations in handling global information and long-range dependencies [3], [4], [5].”
An intelligent and efficient CNN-AES framework for image block encryption with a multi-key approach
Saini, A., & Sehrawat, R. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ada3af · Cited by 11
Benítez, V. H., Pacheco, J., & Cruz, G. C. (2025) · IEEE Access · doi:10.1109/access.2025.3545827 · Cited by 11
“While traditional CNNs are widely recognized for their effectiveness in two-dimensional contexts, such as image analysis, the 1D-CNNs are tailored for examining sequential or temporal data represented in a one-dimensional format [11].”
Abbas, M. J., Khan, M. A., Hamza, A., Alsenan, S. A., Alasiry, A., Marzougui, M., Li, Y., & Nam, Y. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3580801 · Cited by 11
“Pooling layers refine these by reducing spatial dimensions, making the network computationally efficient while preserving critical information [26].”
Research on hyperspectral remote sensing alteration mineral mapping using an improved ViT model
Feng, X., Huang, J., Chen, X., Zhou, H., Zhang, M., Zhang, C., & Ye, F. (2025) · Computers & Geosciences · doi:10.1016/j.cageo.2025.106037 · Cited by 11
The Evolution of Deep Learning: Models, Applications, and Future Directions
Elshenawy, A., Mohammed, A., & Hamouda, S. (2025) · International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC) · doi:10.1109/miucc66482.2025.11196834 · Cited by 11
Eyes of the Future: Decoding the World Through Machine Vision
Khonina, S. N., Kazanskiy, N. L., Oseledets, I. V., Khabibullin, R. M., & Nikonorov, A. V. (2025) · Technologies · doi:10.3390/technologies13110507 · Cited by 11
“Deeper layers then combine these into more complex and abstract features, such as object parts, full shapes, or scene context, enabling robust recognition [81].”
An Efficient Multiple Convolutional Neural Network Model (MCNN-14) for Fashion Image Classification
Saed, S., Teimourpour, B., Kalashi, K., & Soltanshahi, M. A. (2024) · International Conference on Web Research (ICWR) · doi:10.1109/icwr61162.2024.10533341 · Cited by 11
“One notable constraint is their sensitivity to the quality of training data; noisy or biased data can lead the model to learn artifacts rather than underlying patterns [4].”
BackgroundRajagopalan, S., Purohit, A., & Singh, J. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad5b7d · Cited by 11
Zhang, H., Cui, L., Lee, P.-H., Kim, Y., Moon, S. K., & Choi, J. P. (2024) · Virtual and Physical Prototyping · doi:10.1080/17452759.2024.2429530 · Cited by 11
Kuswidiyanto, L. W., Kim, D. E., Fu, T., Kim, K. S., & Han, X. (2023) · Agriculture · doi:10.3390/agriculture13122215 · Cited by 11
Faiz, J., Naseri, H., Ilaghi, H. T., & Samimi, M. H. (2025) · IET Science Measurement & Technology · doi:10.1049/smt2.70014 · Cited by 10
Robrini, F. E., Amrouche, B., Cali, Ü., & Ustun, T. S. (2025) · Energy Conversion and Management X · doi:10.1016/j.ecmx.2025.101108 · Cited by 10
Salazar-Campos, O., Ruiz, J. M., Peralta, J. L., Cieza, M. R., Medina, B. S., & Salazar-Campos, J. (2025) · Results in Control and Optimization · doi:10.1016/j.rico.2025.100589 · Cited by 10
Metadata
- Authors
- Krichen, M.
- Affiliations
- University of Sfax (TN)
- Corresponding author
- Krichen, Moez
- ORCID
- Krichen, Moez
- Venue
- Computers
- Publisher
- MDPI AG
- Published
- 2023-07-28
- Volume
- 12
- Issue
- 8
- Pages
- 151
- ISSN
- 2073-431X (ISSN-L)
- OpenAlex
- W4385342469
- Cited by
- 623
- References
- 199
- Citations by year
- 2026: 144 · 2025: 242 · 2024: 189 · 2023: 48
- FWCI
- 56.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Computers (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- convolutional neural networks, image recognition, convolutional neural network architecture, LeNet, AlexNet, VGG, ResNet, InceptionNet, activation functions, hyperparameter optimization, deep learning libraries, attention mechanism, capsule networks, transfer learning, adversarial training, model compression, formal verification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.