Cited by 3,503Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval Techniques

The DOI matches its Crossref record; 274 of the 286 references it cites were found in a registry or an index.

Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review

Rawat, Waseem, Wang, Zenghui·2017·Neural Computation

DOI 10.1162/neco_a_00990

Open this paper in CoChat — free account

Abstract

Convolutional neural networks (CNNs) have been applied to visual tasks since the late 1980s. However, despite a few scattered applications, they were dormant until the mid-2000s when developments in computing power and the advent of large amounts of labeled data, supplemented by improved algorithms, contributed to their advancement and brought them to the forefront of a neural network renaissance that has seen rapid progression since 2012. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art deep learning systems. Along the way, we analyze (1) their early successes, (2) their role in the deep learning renaissance, (3) selected symbolic works that have contributed to their recent popularity, and (4) several improvement attempts by reviewing contributions and challenges of over 300 publications. We also introduce some of their current trends and remaining challenges.

Integrity signals

Registry

Crossref · 10.1162/neco_a_00990

Cites

274 of 274 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Long Short-Term Memory
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Deep learning
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138

Flagged first, then by citations

Show all 286 references

12 of the 286 references couldn’t be matched to a known paper.

Research works printed but not linked: 86

Abdulkader A., 2006, Proceedings of the 10th International Workshop on Frontiers in Handwriting Recognition, 1
Arora S., 2014, Proceedings of the 31th International Conference Machine Learning, 584
Ba J., 2013, Advances in neural information processing systems, 26, 3084
Ba J., 2015, Proceedings of the 3rd International Conference on Learning Representations, 1
Bachman P., 2016, Advances in neural information processing systemsm, 29, 4826
Baldi P., 2013, Advances in neural information processing systems, 26, 3084
Belkin M., 2006, Journal of Machine Learning Research, 7, 2399
Bengio Y., 2014, Proceedings of the 31st International Conference Machine Learning, 226
Bulo S., 2014, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 81
Chellapilla K., 2006, Proceedings of the 10th International Workshop on Frontiers in Handwriting Recognition.
Chellapilla K., 2006, Proceedings of the 18th Annual Symposium on Electronic Imaging, 6067
Chellapilla K., 2006, Proceedings of the 10th Internstional Workshop on Frontiers in Handwriting Recognition, 1
Choromanska A., 2015, Proceedings 18th International Conference on Artificial Intelligence and Statistics, 192
Clevert D., 2016, Proceedings of the 4th International Conference on Learning Representations, 1
Coates A., 2011, Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, 215
Collobert R., 2006, Journal of Machine Learning Research, 7, 1687
Courbariaux M., 2015, Advances in neural information processing systems, 28, 3123
Courbariaux M., 2016, Advances in neural information processing systems, 29, 1
Deng L., 2014, APSIPA Transactions on Signal and Information Processing, 3, 1
Denil M., 2013, Advances in neural information processing systems, 26, 2148
Denton E. L., 2014, Advances in neural information processing systems, 27, 1269
Dettmers T., 2016, Proceedings of the 4th International Conference on Learning Representations, 1
Duchi J., 2011, Journal of Machine Learning Research, 12, 2121
Erhan D., 2010, Journal of Machine Learning Research, 11, 625
Filho D. P., 2009, Proceedings of the XXII Brazilian Symposium on Computer Graphics and Image Processing, 1
Fukushima K., 1979, Proceedings of the 6th International Joint Conference on Artificial Intelligence, 291
Glorot X., 2010, Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, 249
Glorot X., 2011, Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, 315
Goodfellow I., 2016, Deep learning
Goodfellow I., 2014, Advances in neural information processing systems, 27, 2672
Goodfellow I. J., 2015, Proceedings of the 3rd International Conference on Learning Representations, 1
Goodfellow I. J., 2013, Proceedings of the 30th International Conference Machine Learning, 1319
Han S., 2016, Proceedings of the 3rd International Conference on Learning Representations, 1
Huang G. B., 2007, Labeled faces in the wild: A database for studying face recognition in unconstrained environments
Iandola F. N., 2016, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 1MB model size
Ioffe S., 2015, Proceedings of the 32nd International Conference Machine Learning, 448
Jaderberg M., 2015, Advances in neural information processing systems, 28, 2017
Jin J., 2016, Proceedings of the 4th International Conference on Learning Representations, 1
Karpathy A., 2016, CS231n: Convolutional neural networks for visual recognition
Karpathy A., 2016, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3128
Kennedy J., 1995, Proceedings of the 6th International Symposium on Micro Machine and Human Science, 39
Krizhevsky A., 2012, Advances in neural information processing systems, 25, 1097
Kulkarni T. D., 2015, Advances in neural information processing systemsm, 28, 2539
Lebedev V., 2014, Speeding-up convolutional neural networks using fine-tuned CP-decomposition
LeCun Y., 1989, Connections in perspective, 143
LeCun Y., 1989, Advances in neural information processing systems, 2, 396
Lee C., 2015, Proceedings of the 18th International Conference on Artificial Intelligence and Statistics, 562
Leibo J. Z., 2011, Advances in neural information processing systems, 24, 711
Levine S., 2016, Journal of Machine Learning Research, 17, 1
Li S., 2016, Demystifying ResNet
Li Z., 2016, Advances in neural information processing systemsm, 1
Lin M., 2013, Network in network
Linnainmaa S., 1970, The representation of the cumulative rounding error of an algorithm as a Taylor expansion of the local rounding errors
Liu W., 2016, Proceedings of the 33rd International Conference Machine Learning, 507
Maas A. L., 2013, Proceedings of the 30th International Conference Machine Learning, 1
Maharaj A. V., 2015, Improving the adversarial robustness of ConvNets by reduction of input dimensionality
Mishkin D., 2016, Proceedings of the 4th International Conference on Learning Representations, 1
National Data Science Bowl | Kaggle, 2016, Kaggle.com
Netzer Y., 2011, Advances in neural information processing systems, 24 (NIPS) Workshop on Deep Learning and Unsupervised Feature Learning, 1
Novikov A., 2015, Advances in neural information processing systems, 28
Ranzato M., 2006, Advances in neural information processing systems, 19, 1137
Recht B., 2011, Advances in neural information processing systems, 24, 693
Rippel O., 2014, Proceedings of the 30th International Conference on Machine Learning, 1746
Rippel O., 2015, Advances in neural information processing systems, 28, 2449
Romero A., 2015, Proceedings of the 3rd International Conference on Learning Representations, 1
Sabour S., 2016, Proceedings of the 4th International Conference on Learning Representations, 1
Sermanet P., 2012, Proceedings of the 21st International Conference on Pattern Recognition, 3288
Snoek J., 2012, Advances in neural information processing systems, 25, 2951
Sontag E. D., 1998, NATO ASI Series F Computer and Systems Sciences, 168, 69
Srivastava N., 2014, Journal of Machine Learning Research, 15, 1929
Srivastava N., 2013, Advances in neural information processing systems, 26, 2094
Srivastava R. K., 2015, Advances in neural information processing systems, 28, 2377
Srivastava R. K., 2015, Highway networks
Steinkrau D., 2005, Proceedings of the 8th International Conference on Document Analysis and Recognition, 1115
Stollenga M. F., 2014, Advances in neural information processing systems, 27, 3545
Sun Y., 2014, Advances in neural information processing systems, 27, 1988
Sutskever I., 2013, Proceedings of the 30th International Conference Machine Learning, 1139
Szegedy C., 2014, Proceedings of the 1st International Conference on Learning Representations, 1
Wager S., 2013, Advances in neural information processing systems, 26, 351
Wan L., 2013, Proceedings of the 30th International Conference Machine Learning, 1058
Wang S. I., 2013, Proceedings of the 30th International Conference Machine Learning, 118
Wang Y., 2016, Advances in neural information processing systems, 29, 1
Weinberger K. Q., 2005, Advances in neural information processing systems, 18, 1473
Yang J., 2009, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1794
Zhai S., 2016, Advances in neural information processing systems, 29, 1
Zinkevich M., 2010, Advances in neural information processing systemsm, 23, 2595

Sorted by citations

Items 301–400 of 1,000

Applications of deep learning in electron microscopy
Treder, K. P., Huang, C., Kim, J. S., & Kirkland, A. I. (2021) · Microscopy · doi:10.1093/jmicro/dfab043 · Cited by 80
“This forms the foundation for more complex operations such as object detection ( f od ) and semantic segmentation ( f seg ) [15].”
Multi-scale deep feature learning network with bilateral filtering for SAR image classification
Geng, J., Jiang, W. R., & Deng, X. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.07.007 · Cited by 73
Precise localization and semantic segmentation detection of printing conditions in fused filament fabrication technologies using machine learning
Jin, Z., Zhang, Z., Ott, J., & Gu, G. X. (2020) · Additive manufacturing · doi:10.1016/j.addma.2020.101696 · Cited by 70
“A pre-trained model is used in each task since it keeps the feature extraction at the front part of the model and only the end part of it is required for training, where the method has been verified in many studies [33,34].”
Method
Two-stage convolutional encoder-decoder network to improve the performance and reliability of deep learning models for topology optimization
Ates, G. C., & GÖRGÜLÜARSLAN, R. M. (2021) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-020-02788-w · Cited by 77
Pre-Trained Convolutional Neural Networks for Breast Cancer Detection Using Ultrasound Images
Masud, M., Hossain, M. S., Alhumyani, H. A., Alshamrani, S. S., Cheikhrouhou, O., Ibrahim, S., Muhammad, G., Rashed, A. E. E., & Gupta, B. B. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3418355 · Cited by 72
Performance comparison of deep learning and machine learning methods in determining wetland water areas using EuroSAT dataset
Günen, M. A. (2021) · Environmental Science and Pollution Research · doi:10.1007/s11356-021-17177-z · Cited by 73
“Access to big data and hardware improvements have accelerated research on the development of the CNN structure (Guidici and Clark 2017; Maggiori et al. 2016; Rawat and Wang 2017).”
Background
Integrated Photonic Tensor Processing Unit for a Matrix Multiply: A Review
Peserico, N., Shastri, B. J., & Sorger, V. J. (2023) · Journal of Lightwave Technology · doi:10.1109/jlt.2023.3269957 · Cited by 74
Learning spatial patterns and temporal dependencies for traffic accident severity prediction: A deep learning approach
Alhaek, F., Liang, W., Rajeh, T. M., Javed, M. H., & Li, T. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111406 · Cited by 71
SLSNet: Skin lesion segmentation using a lightweight generative adversarial network
Sarker, M. M. K., Rashwan, H. A., Akram, F., Singh, V. K., Banu, S. F., Chowdhury, F. U. H., Choudhury, K. A., Chambon, S., Radeva, P. I., Puig, D., et al. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115433 · Cited by 73
“Deep learning-based approaches: Recently, convolutional neural networks (CNNs) have been commonly applied for different tasks, such as image segmentation (Guo et al., 2018), object detection (Zhao et al., 2019) and image classification (Rawat and Wang, 2017).”
Method
Deep convolutional features for image retrieval
Gkelios, S., Sophokleous, A., Plakias, S., Boutalis, Y. S., & Chatzichristofis, S. A. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114940 · Cited by 71
Advances of metaheuristic algorithms in training neural networks for industrial applications
Chong, H.-Y., Yap, H. J., Tan, S. C., Yap, K. S., & Wong, S. Y. (2021) · Soft Computing · doi:10.1007/s00500-021-05886-z · Cited by 74
“Comprehensive reviews of DL have been presented in different applications, which include image processing (Rawat and Wang 2017), natural language processing (Young et al.”
Background
Machine Learning Approach to Model Order Reduction of Nonlinear Systems via Autoencoder and LSTM Networks
Simpson, T., Dervilis, N., & Chatzi, E. (2021) · Journal of Engineering Mechanics · doi:10.1061/(asce)em.1943-7889.0001971 · Cited by 86
“CNNs are effectively and widely used in high dimensional image recognition tasks (Rawat and Wang 2017) and also used in the context of model reduction by Lee and Carlberg (Lee and Carlberg 2020).”
Method
Classification of clustered microseismic events in a coal mine using machine learning
Duan, Y., Shen, Y., Canbulat, I., Luo, X., & Si, G. (2021) · Journal of Rock Mechanics and Geotechnical Engineering · doi:10.1016/j.jrmge.2021.09.002 · Cited by 72
A deep learning approach based hardware solution to categorise garbage in environment
Gupta, T., Joshi, R., Mukhopadhyay, D., Sachdeva, K., Jain, N., Virmani, D., & García‐Hernández, L. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00529-0 · Cited by 70
“Methods (flipping and rotation), and dropout [41].”
Development of Deep Learning Methodology for Maize Seed Variety Recognition Based on Improved Swin Transformer
Bi, C., Hu, N., Zou, Y., Zhang, S., Xu, S., & Yu, H. (2022) · Agronomy · doi:10.3390/agronomy12081843 · Cited by 72
A review of distributed solar forecasting with remote sensing and deep learning
Chu, Y., Wang, Y., Yang, D., Chen, S., & Li, M. (2024) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2024.114391 · Cited by 87
Deep Learning for Classification of the Chemical Composition of Particle Defects on Semiconductor Wafers
O'Leary, J., Sawlani, K., & Mesbah, A. (2020) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2019.2963656 · Cited by 71
Deep learning for reconstructing protein structures from cryo-EM density maps: Recent advances and future directions
Giri, N., Roy, R. S., & Cheng, J. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102536 · Cited by 59
“, convolutional neural network (CNN) [32], U-Net [33, 42], graph convolutional network (GCN) [40], and long- and short-term memory network (LSTM) [41] they use and the output (e.”
Method
Towards Device-Agnostic Mobile Cough Detection with Convolutional Neural Networks
Barata, F., Kipfer, K., Weber, M., Tinschert, P., Fleisch, E., & Kowatsch, T. (2019) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi.2019.8904554 · Cited by 70
“In recent years, CNNs have been one of the most frequently used architectures in the context of computer vision [42].”
Method
Explainable Artificial Intelligence for Developing Smart Cities Solutions
Thakker, D., Mishra, B. K., Abdullatif, A., Mazumdar, S., & Simpson, S. (2020) · Smart Cities · doi:10.3390/smartcities3040065 · Cited by 75
Recognition of carrot appearance quality based on deep feature and support vector machine
Zhu, H., Yang, L., Fei, J., Zhao, L., & Han, Z. (2021) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2021.106185 · Cited by 70
A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
Zhang, H., & Vargas, D. V. (2023) · IEEE Access · doi:10.1109/access.2023.3299296 · Cited by 82
“3 demonstrates the filtering by the traditional moving average method, the deep learning method [3], and our proposed RC approach to jointly sense and minimize the 1/f noise in the input MCG signal.”
BackgroundMethodInfluential
Machine learning applications in forensic DNA profiling: A critical review
Barash, M., McNevin, D. B., Fedorenko, V. A., & Giverts, P. (2023) · Forensic Science International Genetics · doi:10.1016/j.fsigen.2023.102994 · Cited by 78
COVID-19 Pandemic Forecasting Using CNN-LSTM: A Hybrid Approach
Zain, Z. M., & Alturki, N. M. (2021) · Journal of Control Science and Engineering · doi:10.1155/2021/8785636 · Cited by 70
“Convolutional and pooling layers [44] function as purpose-built data preprocessing layers, filtering incoming data, and extracting important information to be used as an input to a fully connected network layer.”
Background
Promoting smart tourism personalised services via a combination of deep learning techniques
Kontogianni, A., Alepis, E., & Patsakis, C. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115964 · Cited by 68
Electromechanical Impedance Temperature Compensation and Bolt Loosening Monitoring Based on Modified Unet and Multitask Learning
Du, F., Wu, S., Xu, C., Yang, Z., & Su, Z. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3132943 · Cited by 68
“olution of input features, making the network have translation invariance and scaling invariance to the input [38].”
Background
Histogram of Oriented Gradients meet deep learning: A novel multi-task deep network for 2D surgical image semantic segmentation
Bhattarai, B., Subedi, R., Gaire, R. R., Vazquez, E., & Stoyanov, D. (2022) · Medical Image Anal. · doi:10.1016/j.media.2023.102747 · Cited by 73
“With the usage of deep learning algorithms, the accuracy of computer vision tasks such as classification, segmentation, and detection is improving significantly (Rawat and Wang, 2017).”
Method
Spectral and Spatial Classification of Hyperspectral Images Based on Random Multi-Graphs
Gao, F., Wang, Q., Dong, J., & Xu, Q. (2018) · Remote Sensing · doi:10.3390/rs10081271 · Cited by 68
“These methods have been actively studied in image classification [42,43], natural language processing [44], and speech recognition [45], etc.”
Method
Infrastructure Safety Oriented Traffic Load Monitoring Using Multi-Sensor and Single Camera for Short and Medium Span Bridges
Xia, Y., Jian, X., Bin, Y., & Su, D. (2019) · Remote Sensing · doi:10.3390/rs11222651 · Cited by 68
“Compared to the motion-based one, the feature-based method is much more efficient and robust due to the upsurge of deep learning, and is considered to be the mainstream of computer vision techniques [24,25].”
Hematologist‐Level Classification of Mature B‐Cell Neoplasm Using Deep Learning on Multiparameter Flow Cytometry Data
Zhao, M., Mallesh, N., Höllein, A., Schabath, R., Haferlach, C., Haferlach, T., Elsner, F., Lüling, H., Krawitz, P. M., & Kern, W. (2020) · Cytometry Part A · doi:10.1002/cyto.a.24159 · Cited by 72
“However, CNNs require a large number of samples for training to achieve good performance (8,9).”
Background
Downscaling Solar-Induced Chlorophyll Fluorescence Based on Convolutional Neural Network Method to Monitor Agricultural Drought
Zhang, Z., Xu, W., Qin, Q., & Long, Z. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2999371 · Cited by 70
“In the remote sensing field, CNN is often used in image classification and object recognition [72]–[75].”
Method
Quantifying the separability of data classes in neural networks
Schilling, A., Maier, A., Gerum, R. C., Metzner, C., & Krauß, P. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.03.035 · Cited by 76
Deep Convolutional Neural Networks With Ensemble Learning and Generative Adversarial Networks for Alzheimer’s Disease Image Data Classification
Logan, R. A., Williams, B. G., da Silva, M. F., Indani, A., Schcolnicov, N., Ganguly, A., & Miller, S. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.720226 · Cited by 69
RETRACTED ARTICLE: India perspective: CNN-LSTM hybrid deep learning model-based COVID-19 prediction and current status of medical resource availability
Ketu, S., & Mishra, P. K. (2021) · Soft Computing · doi:10.1007/s00500-021-06490-x · Cited by 70
“The ﬁrst part is composed of pooling and consensual layers in which The pooling and convolutional layers (Rawat and Wang 2017) are preprocessing layers that have been used for ﬁltering and extracting fruitful information from the data.”
Method
Retracted
Virus Detection and Identification in Minutes Using Single-Particle Imaging and Deep Learning
Shiaelis, N., Tometzki, A., Peto, L., McMahon, A., Hepp, C., Bickerton, E., Favard, C., Muriaux, D. M., Andersson, M. I., Oakley, S. J., et al. (2022) · ACS Nano · doi:10.1021/acsnano.2c10159 · Cited by 65
Explainable Machine Learning Framework for Image Classification Problems: Case Study on Glioma Cancer Prediction
Pintelas, E. G., Liaskos, M., Livieris, I. E., Kotsiantis, S. B., & Pintelas, P. (2020) · Journal of Imaging · doi:10.3390/jimaging6060037 · Cited by 66
“Image classification is a very popular machine learning domain in which Convolutional Neural Networks (CNNs) [1] have been successfully applied on wide range of image classification problems.”
Background
Integrating Patient Data Into Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review
Höhn, J., Hekler, A., Krieghoff‐Henning, E., Kather, J. N., Utikal, J. S., Meier, F. E., Gellrich, F. F., Hauschild, A., French, L. E., Schlager, J. G., et al. (2021) · Journal of Medical Internet Research · doi:10.2196/20708 · Cited by 74
“Convolutional neural networks (CNNs) are the most successful systems for handling image classification problems [5].”
Artificial intelligence for phase recognition in complex laparoscopic cholecystectomy
Golany, T., Aides, A., Freedman, D., Rabani, N., Liu, Y., Rivlin, E., Corrado, G. S., Matias, Y., Khoury, W., Kashtan, H., et al. (2022) · Surgical Endoscopy · doi:10.1007/s00464-022-09405-5 · Cited by 67
“Deep convolutional neural networks [17, 18] have recently shown state-of-the-art results on image classification tasks [19, 20].”
Background
Synthetic dataset generation for object-to-model deep learning in industrial applications
Wong, M. Z., Kunii, K., Baylis, M., Ong, W. H., Kroupa, P., & Koller, S. (2019) · PeerJ Computer Science · doi:10.7717/peerj-cs.222 · Cited by 71
“We refer readers to [10] for a comprehensive review of the use of Deep CNNs in Image Classification.”
Method
Deep learning approach to detect seizure using reconstructed phase space images
Ilakiyaselvan, N., Khan, A. N., & Shahina, A. (2020) · Journal of Biomedical Research · doi:10.7555/jbr.34.20190043 · Cited by 65
A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?
Cordeiro, F. R., & Carneiro, G. (2020) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi51738.2020.00010 · Cited by 72
“Deep Neural Networks (DNNs) have shown great performance to deal with different computer vision tasks, such as image classification [1], segmentation [2] and object detection [3], to different areas of applications [4]–[6].”
Background
A Review on Industrial Surface Defect Detection Based on Deep Learning Technology
Qi, S., Yang, J., & Zhong, Z. (2020) · International Conference on Machine Learning and Machine Intelligence (MLMI) · doi:10.1145/3426826.3426832 · Cited by 78
“The CNN is a special type of deep feed forward network for classification [4].”
Background
Fast automated detection of COVID-19 from medical images using convolutional neural networks
Liang, S., Liu, H., Gu, Y., Guo, X., Li, H., Li, L., Wu, Z., Liu, M., & Tao, L. (2021) · Communications Biology · doi:10.1038/s42003-020-01535-7 · Cited by 66
Efficient federated convolutional neural network with information fusion for rolling bearing fault diagnosis
Zhang, Z., Xu, X., Gong, W., Chen, Y., & Gao, H. (2021) · Control Engineering Practice · doi:10.1016/j.conengprac.2021.104913 · Cited by 66
A novel approach based on combining deep learning models with statistical methods for COVID-19 time series forecasting
Abbasimehr, H., Paki, R., & Bahrini, A. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06548-9 · Cited by 67
Accelerating Species Recognition and Labelling of Fish From Underwater Video With Machine-Assisted Deep Learning
Marrable, D., Barker, K., Tippaya, S., Wyatt, M., Bainbridge, S. J., Stowar, M., & Larke, J. (2022) · Frontiers in Marine Science · doi:10.3389/fmars.2022.944582 · Cited by 65
“…on learning from labelled datasets and require substantial volumes of accurately data compared with traditional “rule”-based computer vision models (Rawat and Wang, 2017) but can extract ecologically useful information from video footage only when adequately trained (Cutter et al., 2015; Ditria et…”
Dual adaptive training of photonic neural networks
Zheng, Z., Duan, Z., Chen, H., Yang, R., Gao, S., Zhang, H., Xiong, H., & Lin, X. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00723-4 · Cited by 72
“…by deep neural networks (DNNs), uses brain-inspired information processing mechanisms to approach human-level performance in complex tasks 1 , and has already achieved major applications ranging from translating languages 2 , image recognition 3 and cancer diagnosis 4 to fundamental science 5 .”
Background
Classification of mice hepatic granuloma microscopic images based on a deep convolutional neural network
Wang, Y., Chen, Y., Yang, N., Zheng, L., Dey, N., Ashour, A. S., Rajinikanth, V., Tavares, J. M. R. S., & Shi, F. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.10.006 · Cited by 67
Detecting Aedes aegypti mosquitoes through audio classification with convolutional neural networks
Fernandes, M. S., Cordeiro, W., & Recamonde-Mendoza, M. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104152 · Cited by 64
“CNNs are one of the most popular deep learning networks architectures used in computer vision due to their outstanding ability in detecting patterns from images (Rawat and Wang, 2017).”
Background
Deep Learning with Neuroimaging and Genomics in Alzheimer’s Disease
Lin, E., Lin, C., & Lane, H. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22157911 · Cited by 71
“In the CNN model, there are three main types of layers: convolutional layers, pooling layers, and fully connected layers [26,27].”
BackgroundMethod
Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
Robles-Serrano, S., Torres, G. S., & Branch, J. W. (2021) · Computers · doi:10.3390/computers10110148 · Cited by 70
Barriers Related to AI Implementation in Supply Chain Management
Shrivastav, M. (2022) · Journal of Global Information Management · doi:10.4018/jgim.296725 · Cited by 81
“Infact, it has already outperformed humans in image and voice recognition systems as well as personalized search recommendations (Krizhevsky et al., 2012; Rawat & Wang, 2017).”
Background
Deep learning-based approach for detecting COVID-19 in chest X-rays
Şahin, M. E. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103977 · Cited by 66
“As a result, a structure is established in which the most basic to the most complex quality is learned from the lowest to the highest layer [42,43].”
Background
Hybrid deep learning model for automated colorectal cancer detection using local and global feature extraction
Paçal, İ., & Attallah, O. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113625 · Cited by 64
Using Siamese Networks with Transfer Learning for Face Recognition on Small-Samples Datasets
Heidari, M., & Fouladi, K. (2020) · Iranian Conference on Machine Vision and Image Processing · doi:10.1109/mvip49855.2020.9116915 · Cited by 63
“In recent years, with the emergence of deep learning, avalability of big training data, and improvements in hardwares and computational capabilities, “convolutional neural networks” (CNN) are widely used as one of the most important models by many researchers in various computer vision problems such as image classific…”
Background
Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants
Huang, Y., Vadloori, S., Chu, H., Kang, E. Y., Wu, W., Kusaka, S., & Fukushima, Y. (2020) · Electronics · doi:10.3390/electronics9091444 · Cited by 66
“CNNs have been used in image classification, and since 2012, they have exhibited high performance in the diagnosis of diseases [23].”
Method
Early Detection of Stripe Rust in Winter Wheat Using Deep Residual Neural Networks
Schirrmann, M., Landwehr, N., Giebel, A., Garz, A., & Dammer, K. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.469689 · Cited by 63
“The feature learning part of the network is then followed by dense layers, which will decide the final class label (Rawat and Wang, 2017).”
Background
Post-Consumer Textile Waste Classification through Near-Infrared Spectroscopy, Using an Advanced Deep Learning Approach
Riba, J., Cantero, R., Riba-Mosoll, P., & Puig, R. (2022) · Polymers · doi:10.3390/polym14122475 · Cited by 63
“The convolutional layer is a fundamental part of the neural network, because it extracts the relevant information from the input data [39] by applying the convolution operation between the input matrix and a filter of a given size.”
Method
Electrocardiogram Signals Classification Using Deep-Learning-Based Incorporated Convolutional Neural Network and Long Short-Term Memory Framework
Eleyan, A., & Alboghbaish, E. (2024) · Computers · doi:10.3390/computers13020055 · Cited by 76
“Deep neural networks (DNNs), specifically convolutional neural networks (CNNs), have been revolutionizing classification tasks for more than a decade and have reached impressive performance levels [2].”
Background
SHAP value-based ERP analysis (SHERPA): Increasing the sensitivity of EEG signals with explainable AI methods
Sylvester, S., Sagehorn, M., Gruber, T., Atzmueller, M., & Schöne, B. (2024) · Behavior Research Methods · doi:10.3758/s13428-023-02335-7 · Cited by 68
Monitoring sugar crystallization with deep neural networks
Zhang, J., Meng, Y., Wu, J., Qin, J., Wang, H., Yao, T., & Yu, S. (2020) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2020.109965 · Cited by 66
Landslide Susceptibility Mapping Using Feature Fusion-Based CPCNN-ML in Lantau Island, Hong Kong
Chen, Y., Ming, D., Ling, X., Lv, X., & Zhou, C. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3066378 · Cited by 62
“With the rapid development of computer technology, deep learning (DL) models outperform traditional ML models in image classification [33], object detection [34], speech recognition [35], etc.”
Background
A comprehensive review on intelligent traffic management using machine learning algorithms
Modi, Y., Teli, R., Mehta, A. J., Shah, K., & Shah, M. (2021) · Innovative Infrastructure Solutions · doi:10.1007/s41062-021-00718-3 · Cited by 67
“Softmax is used for multi-class classification [61].”
An Outlook for Deep Learning in Ecosystem Science
Perry, G. L. W., Seidl, R., Bellvé, A. M., & Rammer, W. (2022) · Ecosystems · doi:10.1007/s10021-022-00789-y · Cited by 72
A convolutional neural network STIFMap reveals associations between stromal stiffness and EMT in breast cancer
Stashko, C., Hayward, M.-K., Northey, J. J., Pearson, N., Ironside, A. J., Lakins, J. N., Oria, R., Goyette, M.-A., Mayo, L. N., Russnes, H. G., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-39085-1 · Cited by 65
A proposed method for landslide detection based on transfer learning and graph neural network
Luo, W., Qiu, H., Wei, Y., Huangfu, W., & Yang, D. (2025) · Geoscience Frontiers · doi:10.1016/j.gsf.2025.102171 · Cited by 62
Blister Defect Detection Based on Convolutional Neural Network for Polymer Lithium-Ion Battery
Ma, L., Xie, W., & Zhang, Y. A. (2019) · Applied Sciences · doi:10.3390/app9061085 · Cited by 65
Towards the automation of early-stage human embryo development detection
Raudonis, V., Paulauskaitė-Tarasevičienė, A., Šutienė, K., & Jonaitis, D. (2019) · BioMedical Engineering OnLine · doi:10.1186/s12938-019-0738-y · Cited by 50
“Therefore, we employed CNNs to construct an embryo cell classification system, since CNNs have become one of the most widely used models of deep learning and demonstrate high accuracy performance results in various image recognition tasks [42, 43].”
Method
Deep Predictive Coding Network for Object RecognitionPreprint
Wen, H., Han, K., Shi, J., Zhang, Y., Culurciello, E., & Liu, Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04762 · Cited by 68
Design of synthetic promoters for cyanobacteria with generative deep-learning model
Seo, E., Choi, Y.-N., Shin, Y. R., Kim, D., & Lee, J. W. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad451 · Cited by 61
Automatic Handgun Detection with Deep Learning in Video Surveillance Images
Salido, J., Lomas, V., Ruiz-Santaquiteria, J., & Déniz, Ó. (2021) · Applied Sciences · doi:10.3390/app11136085 · Cited by 70
“Classification [11]: Given an image of a foreground object, the objective is to indicate what is the label or class that identifies that type of object (see the example in Figure 2a); 2.”
Towards a topological–geometrical theory of group equivariant non-expansive operators for data analysis and machine learning
Bergomi, M. G., Frosini, P., Giorgi, D., & Quercioli, N. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0087-3 · Cited by 60
A PM2.5 concentration prediction model based on multi-task deep learning for intensive air quality monitoring stations
Zhang, Q., Wu, S. W., Wang, X., Sun, B., & Liu, H. (2020) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2020.122722 · Cited by 60
A Meta-Analysis of Convolutional Neural Networks for Remote Sensing Applications
Ghanbari, H., Mahdianpari, M., Homayouni, S., & Mohammadimanesh, F. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3065569 · Cited by 68
“Early efforts reviewing CNNs generally was performed by Rawat and Wang [54] in which the authors”
Method
Rapid classification of soils from different mining areas by laser-induced breakdown spectroscopy (LIBS) coupled with a PCA-based convolutional neural network
Hao, W., Hao, X., Yang, Y., Liu, X., Liu, Y., Sun, P., & Sun, R. (2021) · Journal of Analytical Atomic Spectrometry · doi:10.1039/d1ja00078k · Cited by 59
Developing Cybersecurity Systems Based on Machine Learning and Deep Learning Algorithms for Protecting Food Security Systems: Industrial Control Systems
Alkahtani, H. S., & Aldhyani, T. H. H. (2022) · Electronics · doi:10.3390/electronics11111717 · Cited by 60
“It is used to model and convert data from a high-space dimension to a low-space dimension by categorizing the data into regular and harmful packets and transforming the data between the two groups [41].”
Method
Multi-Learner Based Deep Meta-Learning for Few-Shot Medical Image Classification
Jiang, H., Gao, M., Li, H., Jin, R., Miao, H., & Liu, J. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3215147 · Cited by 60
“(1) In our model, F AE is a fully CNN and H E n is also regarded as shared network layers of the feature extractor.”
BackgroundInfluential
Continual All-in-One Adverse Weather Removal With Knowledge Replay on a Unified Network Structure
Cheng, D., Ji, Y., Gong, D., Li, Y., Wang, N., Han, J., & Zhang, D. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3377136 · Cited by 60
“V ARIOUS types of adverse weather, for example, haze, rain, and snow, are ubiquitous in photography, which degenerate the imaging quality and thus hinder the other down-stream computer vision tasks, e.g. , object detection [1], image classiﬁcation [2], semantic segmentation [3], and many others…”
RGB-D-Based Object Recognition Using Multimodal Convolutional Neural Networks: A Survey
Gao, M., Jiang, J., Zou, G., John, V., & Liu, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2907071 · Cited by 63
A Novel Evaluation Metric for Deep Learning-Based Side Channel Analysis and Its Extended Application to Imbalanced Data
Zhang, J., Zheng, M., Nan, J., Hu, H., & Yu, N. (2020) · IACR Transactions on Cryptographic Hardware and Embedded Systems · doi:10.46586/tches.v2020.i3.73-96 · Cited by 60
ADSCNet: asymmetric depthwise separable convolution for semantic segmentation in real-time
Wang, J., Xiong, H., Wang, H., & Nian, X. (2019) · Applied Intelligence · doi:10.1007/s10489-019-01587-1 · Cited by 60
“Building convolutional neural networks has achieved extraordinary progress in many computer vision tasks, such as image classification [32, 34, 39], object detection [11, 40], image retrieval [37, 41], and semantic segmentation [4, 42, 43].”
Method
Deep Feature Space: A Geometrical Perspective
Kansizoglou, I., Bampis, L., & Gasteratos, A. C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3094625 · Cited by 62
Advanced Fully Convolutional Networks for Agricultural Field Boundary Detection
Taravat, A., Wagner, M. P., Bonifaçio, R., & Petit, D. (2021) · Remote Sensing · doi:10.3390/rs13040722 · Cited by 59
“It further revealed that multiple consecutive small-scale convolutions contain more nonlinear expressions than a single large-scale convolution and that smaller-sized convolution kernels can reduce the computation cost and hasten convergence [20].”
Influential
A Predictive Processing Model of Episodic Memory and Time Perception
Fountas, Z., Sylaidi, A., Nikiforou, K., Seth, A. K., Shanahan, M., & Roseboom, W. (2022) · Neural Computation · doi:10.1162/neco_a_01514 · Cited by 61
Urban greenspace and mental health in Chinese older adults: Associations across different greenspace measures and mediating effects of environmental perceptions
Yue, Y., Dong-feng, Y., & Dyck, D. V. (2022) · Health & Place · doi:10.1016/j.healthplace.2022.102856 · Cited by 59
Multimodality of AI for Education: Toward Artificial General Intelligence
Lee, G., Shi, L., Latif, E., Gao, Y., Bewersdorff, A., Nyaaba, M., Guo, S., Liu, Z., Mai, G., Liu, T., et al. (2025) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2025.3574466 · Cited by 199
Deep Learning for Practical Image Recognition
Yang, X., Zeng, Z., Teo, S. G., Wang, L., Chandrasekhar, V., & Hoi, S. C. H. (2018) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3219819.3219907 · Cited by 62
“The interested readers may refer to [17] for a comprehensive review of DCNN for image classification.”
Background
Learning to Classify Structures in ALS-Derived Visualizations of Ancient Maya Settlements with CNN
Somrak, M., Džeroski, S., & Kokalj, Ž. (2020) · Remote Sensing · doi:10.3390/rs12142215 · Cited by 65
A Physics-Informed Neural Network Approach for Nearfield Acoustic Holography
Olivieri, M., Pezzoli, M., Antonacci, F., & Sarti, A. (2021) · Sensors · doi:10.3390/s21237834 · Cited by 58
“The authors, inspired by the effectiveness of learned features for NAH [22] and the well-known feature learning capabilities of deep neural networks (DNN) in the context of acoustics [25–29], proposed a convolutional neural network (CNN) [30] for performing NAH.”
Background
Artificial intelligence in construction asset management: a review of present status, challenges and future opportunities
Rampini, L., & Cecconi, F. R. (2022) · Journal of Information Technology in Construction · doi:10.36680/j.itcon.2022.043 · Cited by 74
The unbearable slowness of being: Why do we live at 10 bits/s?
Zheng, J., & Meister, M. (2024) · Neuron · doi:10.1016/j.neuron.2024.11.008 · Cited by 73
Fast point spread function modeling with deep learning
Herbel, J., Kacprzak, T., Amara, A., Refregier, A. R., & Lucchi, A. (2018) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2018/07/054 · Cited by 62
Dissecting Machine-Learning Prediction of Molecular Activity: Is an Applicability Domain Needed for Quantitative Structure–Activity Relationship Models Based on Deep Neural Networks?
Liu, R., Wang, H., Glover, K., Feasel, M. G., & Wallqvist, A. (2018) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.8b00348 · Cited by 61
Developing a microscopic image dataset in support of intelligent phytoplankton detection using deep learning
Li, Q., Sun, X., Dong, J., Song, S., Zhang, T., Liu, D., Zhang, H., & Han, S. (2019) · ICES Journal of Marine Science · doi:10.1093/icesjms/fsz171 · Cited by 62
Research on highway vehicle detection based on faster R-CNN and domain adaptation
Yin, G., Meng, Y., Wang, M., Hu, Y. S., & Zhang, Y. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02552-7 · Cited by 57
Data augmentation and transfer learning to classify malware images in a deep learning context
Marastoni, N., Giacobazzi, R., & Preda, M. D. (2021) · Journal of Computer Virology and Hacking Techniques · doi:10.1007/s11416-021-00381-3 · Cited by 62
“CNNs are feed-forward neural network models that take inspiration from the human visual cortex and are widely used in image recognition and classification [23,38].”
Background
Sensor and Actuator Fault Diagnosis for Robot Joint Based on Deep CNN
Pan, J., Qu, L., & Peng, K. (2021) · Entropy · doi:10.3390/e23060751 · Cited by 57
“Several typical deep learning methods have been successfully applied to fault diagnosis [23–26], including autoencoders [27], deep belief networks [28], and CNN [29].”
Method
Automated structural bolt looseness detection using deep learning‐based prediction model
Yuan, C., Wang, S.-Y., Qi, Y., & Kong, Q. (2021) · Structural Control and Health Monitoring · doi:10.1002/stc.2899 · Cited by 61
“As deeper-up in the model, more specific features are extracted as compared to a shallow network where the features extracted are more generic.(59) The ith output feature map Fi can be expressed as follows:”
Background
Development of a Robust, Simple, and Affordable Human Gait Analysis System Using Bottom-Up Pose Estimation With a Smartphone Camera
Viswakumar, A., Rajagopalan, V., Ray, T., Gottipati, P., & Parimi, C. (2022) · Frontiers in Physiology · doi:10.3389/fphys.2021.784865 · Cited by 57
Structural engineering from an inverse problems perspective
Gallet, A., Rigby, S. E., Tallman, T. N., Kong, X., Hajirasouliha, I., Liew, A., Liu, D., Chen, L., Hauptmann, A., & Smyl, D. (2022) · Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rspa.2021.0526 · Cited by 66
“More importantly, especially when taking into consideration the recent developments in data science ranging from convolutional neural networks [312], transformers [313] and graph neural networks [314], there exists a vast spectrum of knowledge and applications we may not even be aware of.”
Background

Authors: Rawat, W., & Wang, Z.
Affiliations: University of South Africa (ZA)
ORCID: Wang, Zenghui
Venue: Neural Computation
Publisher: MIT Press
Published: 2017-09
Volume: 29
Issue: 9
Pages: 2352-2449
ISSN: 0899-7667 (ISSN-L)
1530-888X
DOI: 10.1162/neco_a_00990
OpenAlex: W2622826443
Cited by: 3,503
References: 286
Citations by year: 2026: 181 · 2025: 393 · 2024: 470 · 2023: 535 · 2022: 580 · 2021: 589 · 2020: 432 · 2019: 234 · 2018: 84 · 2017: 3
FWCI: 85.59
Type: journal article
Language: en
Open access: closed
Locations: Neural Computation (publishedVersion)
PubMed (publishedVersion)
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 classification, deep learning, history of neural networks, annotated dataset, computer vision

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

Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks