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 201–300 of 869
FocalTransNet: A Hybrid Focal-Enhanced Transformer Network for Medical Image Segmentation
Liao, M., Yang, R., Zhao, Y., Liang, W., & Yuan, J. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3602739 · Cited by 10
“Existing downsampling techniques, such as pooling [18], [19], linear projection [20], [21], and stride convolution [22], [23], usually su ff er from the issue of fine-grained detail loss.”
Shah, S. A. A., Mahrukh, Shah, S. M. A., Wang, S., Niazi, S. G., Xu, Z., & Wu, M. (2026) · Journal of Energy Storage · doi:10.1016/j.est.2026.121207 · Cited by 10
Starke, S., Zwanenburg, A., Leger, K., Lohaus, F., Linge, A., Kalinauskaitė, G., Tinhofer, I., Guberina, N., Guberina, M., Balermpas, P., et al. (2023) · Cancers · doi:10.3390/cancers15194897 · Cited by 10
“Image biomarkers can either be pre-defined and computed in a traditional radiomics workflow or learned from the data using deep learning (DL) techniques that employ, e.g., convolutional neural networks (CNNs) [15,16] or vision transformers (ViTs) [17].”
BackgroundBordbar, M., Heggy, E., Jun, C., Bateni, S. M., Kim, D., Moghaddam, H. K., & Rezaie, F. (2024) · Environmental Science and Pollution Research · doi:10.1007/s11356-024-32706-2 · Cited by 10
“To address the limitations of the CNN model, the implementation of data augmentation and model compression methods, such as pruning and quantization, could be explored (Krichen 2023).”
A Radio Frequency Fingerprinting-Based Aircraft Identification Method Using ADS-B Transmissions
Gurer, G., Dalveren, Y., Kara, A., & Derawi, M. O. (2024) · Aerospace · doi:10.3390/aerospace11030235 · Cited by 10
Guo, Y., Hai, Q., & Bayarsaikhan, S. (2024) · Forests · doi:10.3390/f15081380 · Cited by 10
“They can identify complex, fire-related patterns and features, thereby improving prediction accuracy [82,83].”
BackgroundDeep learning for the detection and classification of adhesion defects in antique plaster layers
Giudice, M. L., Marıanı, F., Calıano, G., & Salvini, A. (2024) · Journal of Cultural Heritage · doi:10.1016/j.culher.2024.07.012 · Cited by 10
Joshua, S. R., Park, S., & Kwon, K.-H. (2024) · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c63300.2024.00045 · Cited by 10
“Due to hierarchical feature extraction, CNNs can recognize intricate patterns and structures inside images, making them ideal for applications such as solar panel fault identification [12].”
Paul, J., Schmid, L., Klaiber, M., & Rössle, M. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.670 · Cited by 10
Benameur, N., Mahmoudi, R., Deriche, M. A., Fayouka, A., Masmoudi, I., & Zoghlami, N. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-10310-x · Cited by 10
“The most common ones are image classification [14,1516] and semantic segmentation using fully convolutional networks (FCNs) [17].”
An Efficient Detector with Auxiliary Network for Remote Sensing Object Detection
Xu, D., & Wu, Y. (2023) · Electronics · doi:10.3390/electronics12214448 · Cited by 10
Performance Insights of Convolutional Neural Networks Operating on Distributed Computing Platforms
Chaudhary, P., Vats, S., & Sharma, V. (2025) · SN Computer Science · doi:10.1007/s42979-025-03893-7 · Cited by 9
The use of artificial intelligence in damage assessment of historical buildings
Ararat, M. B., & Yenice, T. K. (2025) · Frontiers of Architectural Research · doi:10.1016/j.foar.2025.06.008 · Cited by 9
DeepF-SVM: A new hybrid deep learning model for enhanced sensor-based human activity recognition
Charabi, I., Abidine, M. B., Fergani, B., & Oussalah, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05636-y · Cited by 9
“However, CNNs sometimes lead to overfitting, especially in cases where the dataset is small or the classes are imbalanced [48].”
Channel-spatial attention modules in convolutional neural networks for image classification
Zolfaghari, M., Abadeh, M. S., & Sajedi, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-32055-1 · Cited by 9
Yoon, J., Kim, N., Lee, D., Lee, S. J., Kwak, G.-H., & Kim, T. (2023) · Electronics · doi:10.3390/electronics12183964 · Cited by 9
Efficient Channel-Temporal Attention for Boosting RF Fingerprinting
Gu, H., Su, L., Wang, Y., Zhang, W., & Ran, C. (2024) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2024.3362695 · Cited by 9
“Inrecent years, Deep Convolutional Neural Networks (DC-NNs) have made remarkable breakthroughs in a wide range of fields such as computer vision [16], natural language processing [17], and Internet of Things [18], [19], [20], [21].”
BackgroundSideris, N., Bardis, G., Voulodimos, A. S., Miaoulis, G., & Ghazanfarpour, D. (2024) · Sensors · doi:10.3390/s24041335 · Cited by 9
Enhancing Medical Image Retrieval with UMLS-Integrated CNN-Based Text Indexing
Gasmi, K., Ayadi, H., & Torjmen, M. (2024) · Diagnostics · doi:10.3390/diagnostics14111204 · Cited by 9
“In these last years, Convolutional Neural Network (CNN) [7,8] models have shown significant performance improvement in several fields as Natural Language Processing (NLP) [9] and computer vision [10].”
BackgroundJoshua, S. R., Park, S., & Kwon, K.-H. (2024) · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c63300.2024.00048 · Cited by 9
“Artificial intelligence (AI) tools, such as convolutional neural networks (CNNs) and machine learning algorithms, are used to analyze large volumes of data from solar systems [41,42].”
BackgroundBenchmarking YOLO Models for Intracranial Hemorrhage Detection Using Varied CT Data Sources
Tapia, G., Allende‐Cid, H., Chabert, S., Mery, D., & Salas, R. (2024) · IEEE Access · doi:10.1109/access.2024.3510517 · Cited by 9
“In recent years, convolutional neural networks (CNN) [7], which are deep learning (DL) networks, have outperformed conventional ML algorithms in image processing, such as common artificial neural networks, support vector machines, etc. CNNs have been used in several researches as potential tools…”
Cai, W.-Z., Chen, S., Feng, D., & Taciroğlu, E. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103185 · Cited by 9
Bright, T., Adali, S., & Trois, C. (2025) · Drones · doi:10.3390/drones9080550 · Cited by 9
Alghamdi, A. M., Ashraf, M. U., Bahaddad, A. A. S., Almarhabi, K. A., Shehri, W. A. A., & Daraz, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-19727-8 · Cited by 8
A Survey of Machine Learning Techniques for Signal Source Localization and Emitter Tracking
Kaczyński, M., Piotrowski, Z., & Pietrow, D. (2025) · IEEE Access · doi:10.1109/access.2025.3629818 · Cited by 8
“…such as sequences of in-phase (I) and quadrature (Q) components, preserve complete waveform information including amplitude, phase, and fine-grained temporal structures, making them suitable for deep learning architectures like convolutional NNs (CNNs) [9] and recurrent NNs (RNNs) [10].”
Chai, G., Li, S., Yang, Y., Zhou, G., & Wang, Y. (2023) · Sensors · doi:10.3390/s23218793 · Cited by 8
Evaluation of Deformable Convolution: An Investigation in Image and Video Classification
Burgos-Madrigal, A., Romero-Bautista, V., Hernández, R. D., & Altamirano-Robles, L. (2024) · Mathematics · doi:10.3390/math12162448 · Cited by 8
Taxi Demand Method Based on SCSSA-CNN-BiLSTM
Guo, D., Sun, M., Wang, Q., & Zhang, J. (2024) · Sustainability · doi:10.3390/su16187879 · Cited by 8
“[27,28].”
Deep Learning for Traffic Prediction in VANET
Chauhan, S. S., Singh, J., Gupta, G. S., & Pathak, M. K. (2025) · Studies in computational intelligence · doi:10.1007/978-981-96-5190-0_7 · Cited by 8
Javid, I., Ghazali, R., Saeed, W., Batool, T., & Al-wajih, E. (2023) · Sustainability · doi:10.3390/su16010117 · Cited by 8
Classification of MRI brain tumors based on registration preprocessing and deep belief networks
Gasmi, K., Kharrat, A., Ammar, L. B., Ltaifa, I. B., Krichen, M., Mrabet, M., Alshammari, H. H., Yahyaoui, S., Khaldi, K., & Hrizi, O. (2024) · AIMS Mathematics · doi:10.3934/math.2024222 · Cited by 8
Self-citationDeep Feature Extraction with SVM Classifier for Brain Tumor Classification
Alrikabi, J. M., & Muhammad, S. S. (2024) · Journal of education for pure science. · doi:10.32792/jeps.v14i3.539 · Cited by 8
“The convolutional layer, input layer, Batch Normalization(BN) layer, Rectified Linear Unit (RELU) layer, pooling layer, and Fully Connected Layer (FCL) are the main layers that make up the CNN architecture [12].”
BackgroundApplications of generative artificial intelligence in the teaching of customs and international law
Hernández, J. M. M. (2025) · Región Científica · doi:10.58763/rc2025432 · Cited by 8
Convolutional Neural Network approach to classify mitochondrial morphologies
Zaghbani, S., Faber, L., & García‐Sáez, A. J. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108477 · Cited by 7
Ji, Z., Hao, S., Zhao, Q., Yu, Z., Liu, H., Li, L., & Ганчев, И. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324861 · Cited by 7
“In recent years, deep learning networks, particularly Convolutional Neural Networks (CNNs) [14], have made significant advancements in the field of medical image segmentation.”
Behera, R., & Chan, T.-C. (2025) · Journal of the Chinese Institute of Engineers · doi:10.1080/02533839.2025.2548472 · Cited by 7
“By leveraging ANN-based learning, we can develop predictive models that enhance the efficiency of modal analysis while significantly reducing computational costs (Khatir et al. 2024; Krichen 2023).”
Zayed, A., Belhadj, N., Khalifa, K. B., Valderrama, C. A., & Bedoui, M. H. (2025) · Sensors · doi:10.3390/s25175530 · Cited by 7
“The extracted feature maps from the convolutional layers are then flattened into a one-dimensional vector using a Flatten layer [54], which serves as input to a fully connected dense layer containing 128 neurons [55] and a ReLU activation function.”
Mahdavi, N., Daliri, A., Zabihimayvan, M., Yaghooti, Y., Mir, M. A., Ghazanfari, P., Zarrabi, A., Khalaj, P., & Sadeghi, R. (2025) · BioData Mining · doi:10.1186/s13040-025-00486-1 · Cited by 7
“…Quadratic Discriminant Analysis (QDA) [82] eXtreme Gradient Boosting (XGB) [83] Categorical Boosting (CatB) [84] Convolutional Neural Network (CNN) [85] Recurrent Neural Network (RNN) [86] Long Short-Term Memory (LSTM) [87] Multilayer Perceptron (MLP) [88] Autoencoder-Multilayer Perceptron (AMLP)…”
Performance Evaluation of Machine Learning and Deep Learning Models for Credit Risk Prediction
Mapfumo, I., & Shongwe, T. C. (2026) · Journal of risk and financial management · doi:10.3390/jrfm19030210 · Cited by 7
“A CNN applies a series of convolutional filters to capture local patterns in data, which can be useful for identifying clusters of behaviors indicative of credit risk (Krichen, 2023; Salehi et al., 2023).”
Kang, N., Shang, Z., Liu, W., & Huang, X. (2023) · Remote Sensing · doi:10.3390/rs15225367 · Cited by 7
“The convolutional neural network (CNN) is a deep-learning network structure that has been widely applied to image processing and computer vision [22,23].”
BackgroundQi, H., & Han, Z. (2024) · IEEE Access · doi:10.1109/access.2024.3370431 · Cited by 7
“…with convolutional kernels to extract features from input data, pooling layers to reduce the size of feature maps and computational complexity, activation functions for introducing non-linearity, and fully connected layers for the final layer connection to perform classification or regression [29].”
MethodEnhanced Thermal Human Detection in Military Applications Using Deep Learning
Elgohary, R., Mahmoud, A. K., Khaled, O., Salah, S., & Badawi, M. B. (2024) · International Telecommunications Conference (ITC-Egypt) · doi:10.1109/itc-egypt61547.2024.10620540 · Cited by 7
“Kermanidis et al. [11] these AI-powered technologies improve the capacities of security guards, first responders, and surveillance operators by streamlining the human detection process and facilitating real-time analysis and decision-making discussed by Oliveira and Bollen [12] Within this…”
BackgroundPredicting enhanced diagnostic models: deep learning for multi-label retinal disease classification
Sundararajan, S., Harikrishnan, R., Gupta, H., & Patil, Y. (2024) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v14.i1.pp54-61 · Cited by 7
“These conditions, notorious for their potential to impair vision, are increasingly being detected with advanced computational approaches, notably convolutional neural networks (CNNs) [4].”
A new robust AI/ML based model for accurate forensic age estimation using DNA methylation markers
Mathew, J. A., Paul, G., Jacob, J., Kumar, J., Dubey, N., & Philip, N. S. (2025) · Forensic Science Medicine and Pathology · doi:10.1007/s12024-025-00985-x · Cited by 7
“CNNs are deep learning models effective for analyzing spa - tial relationships in data, making them ideal for tasks like feature extraction [ 70, 71].”
Yoon, J.-S., Okwuosa, C. N., Aronwora, N. C., & Hur, J.-W. (2025) · Sensors · doi:10.3390/s25082449 · Cited by 7
“Factors such as image resolution, data augmentation, normalization, and input channels (e.g., grayscale, RGB, or RGBA) must align with the input layer format to ensure optimal performance [43,44].”
InfluentialZhu, D. H. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251341490 · Cited by 7
Enhanced retinal blood vessels segmentation using deep learning and residual network
Lamrani, D., Cherradi, H., Elasri, A., Moujahid, H., Saleh, S., Cherradi, B., & Bahatti, L. (2025) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2025.100263 · Cited by 7
Efficient gesture recognition in Indian sign language using SENet fusion of multimodal data
Nadaf, A. I., Pardeshi, S. A., & Gupta, R. (2025) · Journal of Integrated Science and Technology · doi:10.62110/sciencein.jist.2025.v13.1145 · Cited by 7
A Novel Design of Image Based Object Recognition Model Using Enhanced Neural Classification Logic
Shathik, J. A., Chandra, B. R., Nandeesh, M. D., Manjunath, T. C., Pothala, S., & Lavuri, N. R. (2025) · International Conference on Frontier Technologies and Solutions (ICFTS) · doi:10.1109/icfts62006.2025.11031570 · Cited by 7
Aghaei, A., Pedrielli, G., Wu, T., O’Neill, Z. D., Becerik-Gerber, B., Hoque, S., & Wen, J. (2025) · Building Simulation · doi:10.1007/s12273-025-1278-y · Cited by 7
“Examples are systems for computer vision (CV) (Shanmugamani 2018; Khan et al. 2021; Krichen 2023), expert systems (Abraham 2005; Kumar 2015; Zhang and Lu 2021), and natural language processing (NLP) (Lopez and Kalita 2017; AllenAI n.d.).”
Parsoya, R., Bisht, B., Vlaskin, M. S., Jaiswal, K. K., Chauhan, P. K., Tripathi, M. K., KURBATOVA, A. I., Rajput, V. S., & Kumar, V. (2025) · Cleaner Water · doi:10.1016/j.clwat.2025.100189 · Cited by 7
Crowd-Driven Deep Learning Tracks Amazon Deforestation
McCallum, I., Walker, J., Fritz, S., Grau, M., Hannan, C., Hsieh, I. F., Lape, D., Mahone, J., McLester, C., Mellgren, S., et al. (2023) · Remote Sensing · doi:10.3390/rs15215204 · Cited by 7
“With large advances in recent years in the field of image recognition [24], large image libraries such as those generated via crowdsourcing can be exploited by Artificial Intelligence (AI).”
BackgroundAn Enhanced Deep Learning Scheme for Electromagnetic Imaging of Uniaxial Objects
Chiu, C., Chen, P., Shih, Y.-C., & Lim, E.-H. (2023) · IEEE Transactions on Microwave Theory and Techniques · doi:10.1109/tmtt.2023.3337826 · Cited by 7
“CNN is chosen for this study due to its characteristics listed as follows [26], [27].”
MethodKar, S., McKenna, J. R., Anglada, G., Sunkara, V., Coniglione, R., Stanic, S., & Bernard, L. J. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11101964 · Cited by 7
SC-DiatomNet: An Efficient and Accurate Algorithm for Diatom Classification
Li, J., Jiang, C., Yao, L., & Zhang, S. (2024) · Journal of Marine Science and Engineering · doi:10.3390/jmse12101862 · Cited by 6
Machine Learning for Identifying Pedestrians and Vehicles in Low-Light Images: A Survey
Sabaria, S., & Jeyaprakash, T. (2024) · International Conference on Data Intelligence and Cognitive Informatics (ICDICI) · doi:10.1109/icdici62993.2024.10810913 · Cited by 6
“CNNs have left very few areas of computer vision unexplored and have come to enable computers to extract features from raw images [6] automatically.”
Franco-Gaona, E., Ávila-García, M. S., & Cruz-Aceves, I. (2025) · Mathematics · doi:10.3390/math13040605 · Cited by 6
Khan, A. A., Majid, M. B. A., & Dandoush, A. (2025) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2025.01603113 · Cited by 6
“Convolutional Neural Networks (CNNs), which excel in extracting and analyzing complex visual features, are powerful tools for tasks such as image recognition [5].”
FEP-YOLO: a lightweight steel surface defect detection method for resource-constrained devices
Lu, S., Liang, Y., Ren, Z., Yu, X., & Wang, X. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/aded27 · Cited by 6
Empoasca Pest Attack Classification on Tea Plantations Using Multispectral Imaging and Deep Learning
Kurniawan, B. K., Suratman, F. Y., Fauziah, F., Vidyaningtyas, H., Saputri, D. M., & Pramudita, A. A. (2025) · Emerging Science Journal · doi:10.28991/esj-2025-09-04-04 · Cited by 6
“However, one drawback of CNN is their long training time, although this limitation can be mitigated with modern hardware advancements [17].”
Mapping beam cross-section features to higher-order generalized variables using machine learning
Petrolo, M., Pagani, A., Carrera, E., Candita, G., & Iannotti, P. (2025) · Thin-Walled Structures · doi:10.1016/j.tws.2025.114108 · Cited by 6
Water quality prediction based on LSTM with attention mechanism
Yu, Y., Zhang, H., & Wei, J. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.03.011 · Cited by 6
Wang, X., Li, G., Jia, Z., Feng, X., & Wang, Y. (2023) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/3632956 · Cited by 6
Robust Electric Motor Fault Classification with Extra Trees Classifier on Comprehensive Dataset
Hussain, S. S., & Zaidi, S. S. H. (2024) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai61503.2024.10606973 · Cited by 6
Deep Learning Classification Algorithms Applications: A Review
Kittani, T., & Abdulazeez, A. M. (2024) · Indonesian Journal of Computer Science · doi:10.33022/ijcs.v13i3.4064 · Cited by 6
“Particularly, they are prevalent in face recognition software, effectively discerning intricate patterns and structures within images [18].”
BackgroundWearable Optical Sensors: Toward Machine Learning-Enabled Biomarker Monitoring
Faham, S., Faham, S., & Sepehri, B. (2024) · Chemistry Africa · doi:10.1007/s42250-024-01047-5 · Cited by 6
“One of the advantages of CNNs is their ability to automatically learn classification features at each layer, eliminating the need for manual labeling of features [69].”
Security detection algorithm using CNN: Anomaly detection for API call sequence
Chang, J., Shi, L., Li, Z., Zuo, X., & Hou, B. (2025) · Journal of Computational Methods in Sciences and Engineering · doi:10.1177/14727978251318813 · Cited by 6
Sonkar, C. K., & Kumar, V. (2025) · International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI) · doi:10.1109/ic3ecsbhi63591.2025.10990766 · Cited by 6
Hao, Q., Gan, Q., Liu, Z., Chen, J., Shen, Q., Qian, C., & Liu, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5588-2_41 · Cited by 5
Generative adversarial local density-based unsupervised anomaly detection
Li, X., Peng, J., Li, W., Song, Z., & Du, X. (2025) · PLoS ONE · doi:10.1371/journal.pone.0315721 · Cited by 5
Yahya, A., Lobelo, P., Eram, A., Hussain, S. A., Badruddin, I. A., Bulay-Og, L. L. D., & Albina, D. O. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.106002 · Cited by 5
Mei, Y., Fan, J., Fan, X., & Li, Q. (2025) · Remote Sensing · doi:10.3390/rs17183158 · Cited by 5
Wu, X., Li, Q., Wang, L., Liu, S., Chen, H., Hou, P., Ye, J., Pei, Y., Zhao, X. H., Xie, Y., et al. (2025) · Journal of Materials in Civil Engineering · doi:10.1061/jmcee7.mteng-20664 · Cited by 5
Hussein, A. F., Al-Neami, A. Q., & Al-Qazzaz, N. K. (2025) · International Journal of Information Technology · doi:10.1007/s41870-025-02953-8 · Cited by 5
Real-World Applications of Fuzzy Logic: Bridging Human Reasoning and Machine Intelligence
Ghosh, R., Chakraborty, S., Dutta, G., & Chakraborty, S. (2026) · Information systems engineering and management · doi:10.1007/978-3-032-07922-0_3 · Cited by 5
Elsheref, M., Thapa, P. J., Katwal, A., Naeem, A., Tarr, M. A., & Hoque, M. T. (2026) · Journal of environmental chemical engineering · doi:10.1016/j.jece.2026.121714 · Cited by 5
Novel convolutional neural network for bacterial identification of confocal microscopic datasets
Al-Jumaili, A., Al‐jumaili, S., Alyassri, S., Duru, A. D., Uçan, O. N., Jacob, M. V., Branco, F., Coelho, P. J., & Pires, I. M. (2026) · Scientific Reports · doi:10.1038/s41598-026-38861-5 · Cited by 5
Rezazadeh, S., Azhdari, M., Rezazadeh, G., Pathak, R., Mandl, L., Tautenhahn, H., Tautenhahn, F., Ricken, T., & Seyedpour, S. M. (2026) · International Journal of Heat and Mass Transfer · doi:10.1016/j.ijheatmasstransfer.2026.128932 · Cited by 5
Yousif, J. H., & Yousif, M. J. (2024) · Current Computer Science · doi:10.2174/0129503779282967240315040931 · Cited by 5
Transfer Learning in Building Neural Network Model Case Study
Zorić, M., Štula, M., Markić, I., & Braović, M. (2024) · International Conference on Software, Telecommunications and Computer Networks (SoftCOM) · doi:10.23919/softcom62040.2024.10721924 · Cited by 5
“Specific processing layer types, convolutional and pooling layers handle multi-dimensional visual data [13].”
BackgroundMekruksavanich, S., & Jitpattanakul, A. (2024) · Technologies · doi:10.3390/technologies12120242 · Cited by 5
An improved low‐rank plus sparse unrolling network method for dynamic magnetic resonance imaging
Jiang, M., Chen, Y., Ruan, D., Yuan, Z., Zhang, J., & Xia, L. (2024) · Medical Physics · doi:10.1002/mp.17501 · Cited by 5
Khan, T., Patil, A. N., Singh, A., Bhavsar, G. P., Ashrith, K. S., & Mohanty, S. N. (2025) · Scientific Reports · doi:10.1038/s41598-025-85922-2 · Cited by 5
Decision‐Making in M&A Under Market Mispricing: The Role of Deep Learning Models
Tang, Y. (2025) · Managerial and Decision Economics · doi:10.1002/mde.4533 · Cited by 5
Waste classification using convolutional neural networks tuned by modified metaheuristics algorithm
Tasic, A., Jovanović, L., Popović, M. P., Bačanin, N., Zivkovic, M. Z., & Dobrojević, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-27374-2.00009-1 · Cited by 5
A Deep Equilibrium Model for Remaining Useful Life Estimation of Aircraft Engines
Plakias, S., & Boutalis, Y. S. (2025) · Electronics · doi:10.3390/electronics14122355 · Cited by 5
Mokarram, M., & Pham, T. M. (2025) · Journal of Arid Environments · doi:10.1016/j.jaridenv.2025.105447 · Cited by 5
Pettorru, G., Flumini, M., & Martalò, M. (2025) · Sensors · doi:10.3390/s25154576 · Cited by 5
“The general NTC architecture is illustrated in Figure 3 and is composed of the following layers [30]: Input layer , which receives input data and passes it to the CNN. • Convolutional layer (one or more), which performs a convolution operation on the input data using trainable filters to create a…”
Rienzo, F. D., Madonna, A., Carbonaro, N., Tognetti, A., Virdis, A., & Vallati, C. (2023) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan12050075 · Cited by 5
“As several studies have shown, the use of artificial intelligence (AI) has become a game changer for several sectors such as industry, healthcare, and finance [17].”
Using Machine Learning for Earthquakes and Quarry Blasts Discrimination
Abdalzaher, M. S., Krichen, M., Moustafa, S. S. R., & Alswailim, M. A. (2023) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa59173.2023.10479234 · Cited by 5
Self-citationIbrahim, A. B., Aljasser, F. J., Alowais, S. A., Aldaghri, N., Ragheb, A. M., Almaiman, A., & Alshebeili, S. A. (2024) · Applied Optics · doi:10.1364/ao.520510 · Cited by 5
Liu, H., Deng, X., & Shao, H. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.049737 · Cited by 5
“In tandem with the relentless evolution of deep learning theory, the Convolutional Neural Network (CNN) [46–49] has garnered widespread adoption and commendable success in diverse domains such as face recognition and image segmentation.”
Hybrid Sensing for Fatigue Detection Using Wearables and RF
Taylor, W., Hill, D., Adam, R., Cooper, J. M., Abbasi, Q. H., & Imran, M. A. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3404637 · Cited by 5
“CNNs are successful due to using layers to perform convolution operations that extract features from the input data [36].”
BackgroundClassification Taxonomies Genus of 90 Animals Using Transfer Learning Resnet-152
Saputro, S. N., Adhinata, F. D., & Athiyah, U. (2024) · CommIT (Communication and Information Technology) Journal · doi:10.21512/commit.v18i1.9482 · Cited by 5
“…is a method of the output layer that speeds up the learning process by preventing extreme activation values and functions as a regularize or dropout [17] and 4-dimensional tensor layer, where b is the batch, c is the channel, and the two spatial dimensions are x and y [18], with the Eq.”
MethodZhou, S., Yang, C., Yi, C. X., & Jiao, J. (2025) · Sensors · doi:10.3390/s25020421 · Cited by 5
“He also explored when to use CNNs, their advantages and limitations, and provided recommendations for developers and data scientists [28].”
Baihaqi, G. R., Shalsadilla, S. R., Maulidiya, A. M. N., & Muflikhah, L. (2025) · Optimum: Journal of Economics and Development (University of Ahmad Dahlan Yogyakarta) · doi:10.26555/jiteki.v10i4.30327 · Cited by 5
Ji, Z., Tao, W., & Zhang, L. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ad22be · Cited by 5
AbdelAziz, N. M., Dawood, E. A.-A., Hassan, M. M., & Tantawy, A. A. (2024) · Research Square · doi:10.21203/rs.3.rs-3968021/v1 · Cited by 5
Lyu, Y., Kuswidiyanto, L. W., Wang, P., Noh, H. H., Jung, H., & Han, X. (2025) · Remote Sensing · doi:10.3390/rs17091626 · Cited by 4
High-accuracy classification of banana varieties using ResNet-50 and DenseNet-121 architectures
Riska, S. Y., Sulistyo, D. A., & Maharani, F. S. S. (2025) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v39.i1.pp322-335 · Cited by 4
“CNNs are widely used for image identification, classification, object detection, and face recognition [11], [30]-[32].”
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.