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 701–800 of 869
Giudice, M. L., Marıanı, F., Calıano, G., Morabito, F. C., & Salvini, A. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-4072-3_24
Mechanical Part Defect Detection Based on Data Augmentation and Transfer Learning
Zhang, D. (2026) · International Conference on Electronics Technology and Artificial Intelligence (ETAI) · doi:10.1109/etai68332.2026.11485089
A Multi-scale feature-based Hybrid Deep Focal Network for psychological emotion recognition
Chen, P. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.04.040
Numerical investigation and acoustic detection of flow boiling regimes in a helical tube
Chen, C.-G., Wang, Y. Q., Li, X.-B., Zhang, H.-N., & Li, F.-C. (2026) · Experimental and Computational Multiphase Flow · doi:10.1007/s42757-025-0271-0
“Given its strong capability for feature extraction and image-based classification (Gu et al., 2018; Krichen, 2023; Taye, 2023), a CNN model is employed to learn the correlation between boiling regimes and acoustic signals.”
Alazawi, R. J., Habeeb, N. J., & Almaliki, A. J. Q. (2026) · Iraqi Journal for Computers and Informatics · doi:10.25195/ijci.v52i1.707
“Through these architectural enhancements, the networks have been able to become deeper, more stable, and more efficient [39] [40] [41] [42].”
Effective Intrusion Detection in Industrial IoT Networks Using a Hybrid GAN-CNN Framework
Bouazzi, A., Benslama, M., Helali, A., & Saadaoui, W. (2026) · IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) · doi:10.1109/ic_aset69920.2026.11502482
Visión inteligente para la detección de defectos en la industria textil
Gil-Arroyo, B. (2025) · Repositorio Institucional de la Universidad de Burgos (University of Burgos) · doi:10.36443/10259/11593
Nisya, K., Surono, S., & Thobirin, A. (2026) · Jurnal Teknik Informatika (Jutif) · doi:10.52436/1.jutif.2026.7.2.5548
Accuracy of Deep Learning Models in Detecting Mandibular Furcation Defects on Panoramic Radiographs
Kurumlu, M., Karacaoğlu, F., Kalkan, M., Ülkü, İ., Akagündüz, E., & Orhan, K. (2026) · Diagnostics · doi:10.3390/diagnostics16101500
Deep Learning-Enabled Medical Image Interpretation for Early and Explainable Disease Identification
Aziz, A. (2026) · International Conference on Smart Electronic Devices and Intelligent Systems (ICSEDIS) · doi:10.1109/icsedis68157.2026.11518048
Wubineh, B. Z., Rusiecki, A., & Halawa, K. (2026) · Scientific Reports · doi:10.1038/s41598-026-52523-6
“The convolutional and pooling layers are used to extract relevant features from the input image, followed by one or more fully connected layers that use these features to make a prediction 43 .”
Artificial intelligence strategies for emotion recognition in cancer pain research
Cascella, M., Zarrella, A., Conti, V., Filippelli, A., Bruno, M. P., Esposito, D., Feo, R. D., Cerrone, V., Guerra, C., Lisio, F. D., et al. (2026) · Exploration of Medicine · doi:10.37349/emed.2026.1001404
SMiLE: safe machine learning via embedded overapproximation
Francobaldi, M. (2026) · AMS Dottorato Institutional Doctoral Theses Repository (University of Bologna) · doi:10.48676/unibo/amsdottorato/12471
Dewi, A. R., Thobirin, A., & Surono, S. (2026) · Jurnal ELTIKOM · doi:10.31961/eltikom.v10i1.2089
Khalid, A., Nooruddin, A., Naved, N., Ahmed, S. M. F., Adnan, N., Suresh, S., Lal, A., & Umer, F. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08590-2
“However, training such models to perform domain-specific task is quite resource-intensive, requiring high quality expert-annotated training datasets and substantial computational power [8].”
Septia, R. (2026) · Digilib Repository Unila (Lampung University)
HGFeNet: A Hypergraph-Based Deep Learning Framework for Improved Topographic Feature Extraction
Srivatsan, N., Sriram, V. S. S., Krithivasan, K., & Priyanga, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-25955-4_4
Transformer-BiLSTM prediction of wheel forces in real-road durability testing
Zou, X., Liu, T., Yuan, D. M., Zhang, Y., Yang, H., Huang, C., Yin, C., Guo, Y., Zhang, H., & Zou, J. (2026) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070261451937
Abelly, E. N., Yang, F., Lupyana, S. D., & Kawamala, M. (2026) · Energy & Fuels · doi:10.1021/acs.energyfuels.6c00931
Cordero-Martínez, R., Sánchez, D., & Melín, P. (2026) · AI & Innovation · doi:10.1002/aiv2.70008
de Oliveira, M. R., de Souza, F. D., & da Silva, V. B. (2026) · Artefactum · doi:10.23900/artefactum.v25i2.2777
Carneiro, M. T. (2026) · Institutional Repository of the Federal Technological University of Paraná (RIUT) (Federal University of Technology – Paraná)
Farmland Visual Navigation with Semantic Segmentation Under Leaf Occlusion
Liang, J., Liu, C., Zhai, Y., Zhang, M., & Xu, Y. (2026) · Agriculture · doi:10.3390/agriculture16111205
“In contrast, lightweight fully convolutional architectures [21], with their compact parameter size and fast inference speed, represent the optimal choice for farmland visual navigation.”
Klasifikasi Penyakit Ayam Berdasarkan Citra Kotoran Menggunakan CNN dengan Xception
Mitasya, S. A., Prabowo, A., & Tundjungsari, V. (2026) · Jurnal Informatika Polinema · doi:10.33795/jip.v12i3.9247
KLASIFIKASI PENYAKIT DAUN ANGGUR MENGGUNAKAN FINE-TUNED MOBILENETV3
Baihaqi, I. (2026) · JATI (Jurnal Mahasiswa Teknik Informatika) · doi:10.36040/jati.v10i3.18314
Kanakamedala, P., Manasa, B., Dhanush, C., Vardhan, V. H., & Balusa, B. C. (2026) · International Conference on Emerging Trends in Advancements and Applications of Computational Intelligence Techniques (ETAACT) · doi:10.1109/etaact69135.2026.11542018
“To overcome these challenges, deep learning solutions based on Convolutional Neural Networks (CNNs) have become the most popular solution in the last decade [10].”
Sahani, P., & Singh, A. (2026) · International Conference on Intelligent Systems in Engineering, Secured Systems and Cybersecurity (ICISESSC) · doi:10.1109/icisessc68634.2026.11542726
Subhan, S., Indirawati, N. A., & Ifriza, Y. N. (2026) · International Conference on Pervasive Computing and Social Networking (ICPCSN) · doi:10.1109/icpcsn68523.2026.11543794
“Data collection involves gathering relevant data for algorithm input from various sources like APIs, databases, and sensors [17].”
Wu, Z., Chen, Y., Liu, L., Du, L., & Sun, Y. (2026) · Textile Research Journal · doi:10.1177/00405175251392149
MULTI-ARCHITECTURE DEEP LEARNING FOR SUBJECT INDEPENDENT FACIAL EXPRESSION RECOGNITION
Taufiq, Muhammad, Asran, Ezwarsyah, & Muthalib, M. A. (2026) · JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) · doi:10.33480/jitk.v11i4.7404
“Modern CNN families differ primarily in how they balance representational depth, attention to discriminative regions, and computational efficiency [10], properties that motivate the comparative scope of the present study.”
Baddepuram, C. A., Dawod, Z., & Sharif, M. S. (2025) · International Conference on Data Analytics for Business and Industry (ICDABI) · doi:10.1109/icdabi67967.2025.11547751
“Block 1: Convolution and Pooling The first block consists of a convolutional layer that extracts low-level features such as edges and corners [18], , followed by a max-pooling layer to reduce spatial dimensions.”
Hyperspectral Fingerprints of Abdominal and Pelvic Organs
van de Weerd, L. S., van de Berg, N. J., Rijstenberg, L. L., van de Laar, R. L. O., & van Beekhuizen, H. J. (2026) · Journal of Imaging · doi:10.3390/jimaging12060262
“Once trained, it can be used to make predictions based on new data [17].”
Lu, W., Wang, T., Zhao, Y., Yang, Y., Hu, Y., Song, Y., & Liu, Z. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115745
Opacity predictions in plasmas under stellar conditions using deep learning
Benredjem, D. E., & Pain, J. (2026) · Physical review. E · doi:10.1103/f237-bqz2
Policy and Governance of Artificial Intelligence: Principles and Practices
Ali, A. (2026) · CRC Press eBooks · doi:10.1201/9781003776659
Artificial intelligence enhanced circular economy and sustainable business models
Gupta, A., Loya, A. R., Singh, N., & Kant, S. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-48507-7.00019-5
Analysis of a Person’s Origin Based on Facial Data
Foltýn, T. (2026) · Brno University of Technology Digital Library (Brno University of Technology)
Feature Selection for Improving ANN and CNN Models for Attack Detection in Zeek Network Data
Bagui, S. S., Elbatouty, M., Mink, D., & Bagui, S. (2026) · Future Internet · doi:10.3390/fi18070333
Kumar, R., Jain, A., & Nagar, S. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-27117-4_29
A Lightweight Network Based on Multi-Attention Mechanisms for Metal Surface Defect Detection
Jiang, Y., & Zhang, X. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11560261
A lightweight improved YOLOv11 framework for intracranial hemorrhage detection
Zheng, Y., Du, M., Chang, Q., Wu, J., Han, L., An, Z., & Ye, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-58642-4
Deep Learning CNN Untuk Identifikasi Gulma Berkhasiat Obat
Kusnadi, K., Melati, R., & Arrasyid, Q. (2026) · Jurnal Ners · doi:10.31004/jn.v10i1.52667
Sakka, M. E., Chaâri, L., & Mothe, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37682-4_38
YOLOv8-Based Detection and Classification of Stingless Bee Species from Field Images
Gutierrez, J. G., Cuaresma, N. S. R. P., & Jacinto, A. B. E. (2026) · IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE) · doi:10.1109/iscaie68866.2026.11576412
“Convolutional neural networks have demonstrated remarkable success in fine-grained image classification tasks across various biological domains [10], [11], including insect identification [12].”
AI in Industrial Quality Control: From Algorithms to Operational Impact
Kayyali, M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9725-2.ch012
Artificial Intelligence in Industrial Quality Control: From Algorithms to Operational Impact
Kayyali, M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9725-2.ch015
Wang, Y. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-95-8876-3_64
An Efficient Key-Frame Feature Extraction Method for Object Identification in Videos
Yara, S. (2026) · International Conference on Connected Intelligence for Industrial Applications (CI2A) · doi:10.1109/ci2a69097.2026.11577017
“[8] convolutional neural It can not extract the net-works (CNNs) low-level features of the object.”
Shakib, M. S., Bhuiyan, N. H., Zaman, K., Taibin, M. S. A., Hossen, E., Ali, M. E., & Khisa, R. (2026) · Physiological and Molecular Plant Pathology · doi:10.1016/j.pmpp.2026.103371
Digital Economy Market Forecasting Model Based on Deep Learning Algorithm
ZHU, J. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-95-8876-3_56
Pasya, J. A. P., & Fachrie, M. (2026) · Journal of Information System Research (JOSH) · doi:10.47065/josh.v7i2.8709
“CNN efektif dalam tugas – tugas pengenalan pola karena memiliki kemampuan untuk secara otomatis mengekstaksi fitur dari gambar tanpa memerlukan ekstaksi fitur manual seperti pada metode tradisional [22].”
PURWARUPA SISTEM KENDALI KECEPATAN KERETA BERBASIS KLASIFIKASI INSPEKSI REL MENGGUNAKAN FASTER R-CNN
Putri, Y. S., Nazaruddin, Y. Y., & Juliastuti, E. (2026) · Transmisi: Jurnal Ilmiah Teknik Elektro · doi:10.14710/transmisi.28.3.167-177
Deep Learning-Based Action Recognition Methods
WANG, M. (2026) · International Conference on Signal Image Processing and Communication (ICSIPC) · doi:10.1109/icsipc69751.2026.11584174
“…deepened network layers by stacking small convolutional kernels, GoogLeNet introduced Inception modules to implement multi-scale feature extraction, and ResNet solved the vanishing gradient problem of deep networks via residual connections, enabling the network to exceed one hundred layers [9].”
Myshkovskyi, Y., & Nazarkevych, M. (2026) · Cybersecurity Education Science Technique · doi:10.28925/2663-4023.2026.33.1239
Girepunje, S., & Singh, P. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.416
Mekruksavanich, S., & Jitpattanakul, A. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.05.057
Pamungkas, Y., Karim, A., Uda, M. N. A., & Hashim, U. (2026) · Journal of Information Systems Engineering and Business Intelligence · doi:10.20473/jisebi.12.2.253-268
“The ReLU function is used as follows: This enables the learning of complex spatial dependencies and mitigates vanishing gradients [25].”
Hybrid method for tracking moving objects in video streams under dynamic observation conditions
Семко, О. В., & Віннічук, Д. (2026) · Environmental Safety and Natural Resources · doi:10.32347/2411-4049.2026.2.230-237
Saleh, M. M., Hussein, E. M., Salih, M. E., & Ahmed, M. A. A. (2026) · Informatics · doi:10.3390/informatics13070118
Irrahman, A., Arief, M., Iskandar, A., Saddami, K., Afdhal, A., Sugiarto, S., & Nasaruddin, N. (2026) · Franklin Open · doi:10.1016/j.fraope.2026.100720
Deep Learning Applications for Automated Dental Arch Form Diagnosis
Shirdel, E., Azizipour, S., Magdalyanova, M., & Ашурко, И. П. (2026) · International Conference on Image Processing and Artificial Intelligence (ICIPAI) · doi:10.1109/icipai70034.2026.11605741
“Among the most common DL architectures, CNNs use convolutional filters to capture patterns and build hierarchical feature representations across layers [5-7].”
Brain tumor detection and classification with Deep Neural Networks
Πέτρου, Α. (2026) · Dione (University of Piraeus)
Coltri, F. J. A. (2026) · Institutional Repository of the Federal Technological University of Paraná (RIUT) (Federal University of Technology – Paraná)
Hanoon, R. H., Farhan, H. R., & Taqi, A. M. (2026) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai69016.2026.11613704
“Maqsood et al. 2025 [22] [24]. where , represents the output value at position (i,j) in the resulting feature map, reflecting the response of the convolutional filter to local patterns in the mammogram image, (cid:14) is the bias, , is the convolution kernel, and , is the input image.”
Fake News Detection with Hybrid CNN-SVM on Data AI and Technology
Lesmana, A., Sibaroni, Y., & Prasetyowati, S. S. (2025) · Building of Informatics Technology and Science (BITS) · doi:10.47065/bits.v7i2.7871
“CNN is known to be effective in extracting spatial features from text data, while SVM excels as a classifier in class separation by optimal margins [3][4].”
Masarat, M., & Bashir, R. (2026) · International Journal of Computer Information Systems and Industrial Management Applications · doi:10.70917/ijcisim-2026-3710
Jasa, H. R. M. W., Wanto, A., & Sormin, R. K. (2026) · Jurnal Teknik Informatika (Jutif) · doi:10.52436/1.jutif.2026.7.3.5649
Sayed, B. T., Shaaban, Z., Shukla, M. B., Sharma, S., Nematov, O., Sapaev, I., Sharma, M. K., Smerat, A., khayyat, A., & Mohebi, A. (2026) · Materials Science in Semiconductor Processing · doi:10.1016/j.mssp.2026.111038
Ávila-García, M. S., Franco-Gaona, E., Cruz-Aceves, I., & Hernández-Aguirre, A. (2026) · International Journal of Combinatorial Optimization Problems and Informatics. · doi:10.61467/2007.1558.2026.v17i4.1213
Lobelo, P., Yahya, A., Mangwala, M., Muhammad, Y., & Edozie, E. (2026) · Discover Applied Sciences · doi:10.1007/s42452-026-09321-6
“For example, CNNs will be resource prohibitive to implement, requiring large, distinct, and well-labeled datasets to prevent overtraining [36].”
Meloni, L., Iacob, L., Mureșanu, S., & Roman, R. (2026) · Research Square · doi:10.21203/rs.3.rs-10576447/v1
Convolutional Neural Networks (CNNs)
Hemmati, A., Rahmani, A. M., Bazikar, F., Moosaei, H., & Pardalos, P. M. (2026) · Springer optimization and its applications · doi:10.1007/978-3-032-20703-6_3
Rahimifar, M. M. (2024) · Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)
Aguirre-Rodriguez, S. M., Reategui, D. A. G., & Sierra-Liñan, F. (2026) · International Journal of Engineering Trends and Technology · doi:10.14445/22315381/ijett-v74i7p117
Hamolia, V., & Melnyk, V. A. (2026) · Parallel Computing · doi:10.1016/j.parco.2026.103211
Djakhdjakha, L., Amrouch, S., Abdelmoumène, H., Bouacida, I., & Farou, B. (2026) · IEEE Access · doi:10.1109/access.2026.3721950
“Their convolutional structure enables the extraction of low-to high-level visual features, while pooling and normalization operations improve robustness and training stability [8], [12].”
Wang, Y., Huang, S.-W., Lee, K.-C., & Cheng, C. (2026) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2025-101693
Impact of quantization on various CNN architectures for bone fracture detection
Krishnan, S., & Sundaresan, Y. B. (2026) · Frontiers in Medical Technology · doi:10.3389/fmedt.2026.1892595
Ethical Governance of AI in Healthcare: Focus on RL-Based Dosing Models
Padhiari, A., & Sharma, N. (2026) · doi:10.1109/iccms69991.2026.11642774
“Convolutional neural networks [2] are widely applied in diagnostic imaging, transformers and large language models assist with clinical documentation and triage, and structured machine learning models support risk prediction tasks such as sepsis detection and mortality scoring.”
Saputri, M. I. S., Surono, S., & Thobirin, A. (2026) · JTAM (Jurnal Teori dan Aplikasi Matematika) · doi:10.31764/jtam.v10i3.37037
“Although CNN has been shown to be highly effective across various image processing applications, its performance largely depends on the architectural design of the network employed (Krichen, 2023; Rangel et al., 2024).”
InfluentialWater Quality Monitoring in the Era of Big Data: Sensors, AI, and Integrated Frameworks
杜鹏 (2026) · Journal of Environmental & Earth Sciences · doi:10.30564/jees.v8i8.13361
Implementasi Aplikasi Web untuk Deteksi Manipulasi Gambar Menggunakan ELA, SRM, dan CNN
Ummah, S. N. R., Anggraeny, F. T., & Junaidi, A. (2026) · CICES · doi:10.33050/cices.v12i2.3917
Xu, J. Y., Guo, Z., Xia, Y., Liu, Z., Feng, X., & Yang, Z. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3725361
“Recent studies have introduced convolutional neural networks (CNNs) [31], [32], autoencoder-based models [33], and generative adversarial networks (GANs) [34] into medical image watermarking.”
Dávalos, R. I. C., Elguera, S. M. H., & Cruz, M. A. (2026) · C&T Riqchary Revista de investigación en ciencia y tecnología · doi:10.57166/riqchary/v8.n1.2026.11
Short-Term Electricity Load Forecasting in Power Systems Using BO-VMD-STGCN
Sun, Z. S., Qu, T., Zhao, Z. Y., Sun, X. D., & Shu, Z. (2026) · Advanced Electromagnetics · doi:10.7716/aem.v15i3.4173
Khan, N. M., Hamad, Q. S., Houran, M. A., Khan, M. K., Zafar, M. H., & Sanfilippo, F. (2026) · Case Studies in Thermal Engineering · doi:10.1016/j.csite.2026.108445
Matue, T., Akinyelu, A. A., & Mase, M. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01203-9
Widyastuti, W. (2026) · Universitas Sanata Dharma Repository (Universitas Sanata Dharma)
Wang, H.-C., & Wu, J. (2026) · IEEE Computer Security Foundations Workshop (CSFW) · doi:10.1109/csf68417.2026.00019
Ferramentas de Suporte à Gestão da Limpeza Urbana: Caso de estudo do Município do Porto
de Sousa, I. B. (2026) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
ARTIFICIAL INTELLIGENCE IN DENTAL CARIES DIAGNOSIS: A NARRATIVE REVIEW
Frumuzache, G.-A., Vrabie, A.-T., Andrian, S., Iovan, G., Nica, I., Rotaru-Costin, A.-T., & Stoleriu, S. (2026) · Romanian Journal of Oral Rehabilitation · doi:10.62610/rjor.2026.1.18.10
Group-size adaptive kernel extension for feature upsampling
Xin, J., Wu, C., Xue, G., & Liu, G. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106183
A Novel LTP and LPQ Framework for Potato Disease Detection under Uncontrolled and Clutter Conditions
Thakur, S., & Ramesh, D. (2026) · Potato Research · doi:10.1007/s11540-026-10133-9
Emotion Analysis for the Protection of Industrial Enterprises and Institutions via the IoT
Uçkan, G., & Oğuzay, E. (2026) · International Conference on Electronics, Engineering Physics and Earth Science (EEPES) · doi:10.3390/engproc2026154017
A Survey on Lightweight Deep Neural Network Architecture Design
Li, Y., Chen, Y., Liang, Q., Lv, S., & Lin, F. (2026) · ACM Computing Surveys · doi:10.1145/3842661
Rad, M. R. S., Feizi, A., & Alizadeh, H. (2026) · Natural Hazards · doi:10.1007/s11069-026-08404-2
An Integrated Feature Fusion Framework for Gerbera Variety Prediction Using Computer Vision
Saha, A., Aich, A., Mukherjee, A., Banerjee, A., & Sengupta, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-27711-4_11
HOG Feature-Based Devanagari Handwritten Digit Recognition Using Three-Layer CNN (TCNN) Model
Mukherjee, C., Mondal, R. A., Paul, P., Pal, S. B., & Chakraborty, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-27151-8_19
Tahmasebzadeh, A., Ghafarian, P., & Sadeghi, M. (2026) · Applied Radiation and Isotopes · doi:10.1016/j.apradiso.2026.112934
Chen, Z., & Guo, H. (2026) · International Journal of Reasoning-based Intelligent Systems · doi:10.1504/ijris.2026.156759
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.