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

Show all 286 references

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 801–900 of 1,000

Deep Federated Machine Learning-Based Optimization Methods for Liver Tumor Diagnosis: A Review
Anter, A. M., & Abualigah, L. (2023) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09901-4 · Cited by 29
“It is made up of three main parts: a fully connected layer, a spatial sampling/pooling layer, and a convolutional layer [98].”
Background
Development of thermodynamically consistent machine-learning equations of state: Application to the Mie fluid
Chaparro, G., & Müller, E. A. (2023) · The Journal of Chemical Physics · doi:10.1063/5.0146634 · Cited by 28
Remote sensing tree classification with a multilayer perceptron
Sumsion, G. R., Bradshaw, M. S., Hill, K., Pinto, L., & Piccolo, S. (2019) · PeerJ · doi:10.7717/peerj.6101 · Cited by 28
Site selectivity of single dopant in high-nickel cathodes for lithium-ion batteries
Kim, S., Yang, Y.-J., Lee, E. G., Kim, M.-S., Go, K., Kim, M., Kim, G., Lee, S., Jo, C., Choi, S., et al. (2024) · Chemical Engineering Journal · doi:10.1016/j.cej.2024.148869 · Cited by 27
A convolutional neural network to identify mosquito species (Diptera: Culicidae) of the genus Aedes by wing images
Sauer, F. G., Werny, M., Nolte, K., de Castro, C. V., Becker, N., Kiel, E., & Lühken, R. (2024) · Scientific Reports · doi:10.1038/s41598-024-53631-x · Cited by 28
“A detailed explanation of its operating principle is given by Rawat and Wang 8 .”
Background
Vision transformer models to measure solar irradiance using sky images in temperate climates
Mercier, T. M., Sabet, A., & Rahman, T. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.122967 · Cited by 30
Tea grading, blending, and matching based on computer vision and deep learning
Guo, J., Zhang, K., Adade, S. Y. S., Lin, J., Lin, H., & Chen, Q. (2024) · Journal of the Science of Food and Agriculture · doi:10.1002/jsfa.14088 · Cited by 27
Diagnosa Tumor Otak Berdasarkan Citra MRI (Magnetic Resonance Imaging)
Suta, I. B. L. M., Hartati, R. S., & Divayana, Y. (2019) · Majalah Ilmiah Teknologi Elektro · doi:10.24843/mite.2019.v18i02.p01 · Cited by 27
“Dalam sebagian besar CNN, metode pooling yang biasa digunakan adalah max pooling dan averange pooling [7].”
Background
A Bayesian-Deep Learning Model for Estimating COVID-19 Evolution in Spain
Cabras, S. (2021) · Mathematics · doi:10.3390/math9222921 · Cited by 27
SSDANet: Spectral-Spatial Three-Dimensional Convolutional Neural Network for Hyperspectral Image Classification
Zhang, X., Wang, Y., Zhang, N., Xu, D., Luo, H., Chen, B., & Ben, G. (2020) · IEEE Access · doi:10.1109/access.2020.3008029 · Cited by 28
“Since other articles have introduced the specific structure of 2-D CNN [61], it will not be covered here.”
Background
The Time Complexity Analysis of Neural Network Model Configurations
LEE, R., & Chen, I.-Y. (2020) · International Conference on Mathematics and Computers in Science and Engineering (MACISE) · doi:10.1109/macise49704.2020.00039 · Cited by 27
“However, designing the neural network model and setting the associated parameters in many occasions is subjective, experience-driven and data sensitive by the analyst [8].”
Background
Fuzzy-Rough Cognitive Networks: Theoretical Analysis and Simpler Models
Concepción, L., Nápoles, G., Grau, I., & Witold Pedrycz, C. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3022527 · Cited by 27
Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear
Suh, S., Jang, J., Won, S., Jha, M., & Lee, Y. O. (2020) · Sensors · doi:10.3390/s20205846 · Cited by 27
“By transforming continuous raw vibration time series data into images, we can now use our data as inputs to the CNN, which has proved its outstanding performance in computer vision [26].”
Method
Automated classification of bacterial cell sub-populations with convolutional neural networks
Tamiev, D., Furman, P., & Reuel, N. F. (2020) · PLoS ONE · doi:10.1371/journal.pone.0241200 · Cited by 28
“A successful demonstration of the capability of modern CNN during the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2012 attracted interest to this field and spiked the development of a variety of more advanced, dense convolutional neural network architectures (DCNN) [17, 18].”
Background
Deep learning classification of early normal-tension glaucoma and glaucoma suspects using Bruch’s membrane opening-minimum rim width and RNFL
Seo, S. B., & Cho, H.-K. (2020) · Scientific Reports · doi:10.1038/s41598-020-76154-7 · Cited by 27
Feasibility of the use of deep learning classification of teat-end condition in Holstein cattle
Porter, I. R., Wieland, M. J., & Basran, P. S. (2021) · Journal of Dairy Science · doi:10.3168/jds.2020-19642 · Cited by 27
UAVs in rail damage image diagnostics supported by deep-learning networks
Bojarczak, P., & Lesiak, P. (2021) · Open Engineering · doi:10.1515/eng-2021-0033 · Cited by 27
“Therefore, in the article, the authors attempted to apply, for the extraction of the rail head and detection of split defects, deep convolutional networks [20, 21], which in recent years have experienced rapid development.”
Background
Transfer Learning with Radio Frequency Signals
Kuzdeba, S., Robinson, J., & Carmack, J. M. (2021) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc49032.2021.9369550 · Cited by 31
“It has allowed for accurate models to be constructed in applications where they previously were not, providing significant timesavings during training [14].”
Multiscale Assay of Unlabeled Neurite Dynamics Using Phase Imaging with Computational Specificity
Kandel, M. E., Kim, E., Lee, Y. J., Tracy, G., Chung, H. J., & Popescu, G. (2021) · ACS Sensors · doi:10.1021/acssensors.1c00100 · Cited by 28
Enhanced Recognition of Amputated Wrist and Hand Movements by Deep Learning Method Using Multimodal Fusion of Electromyography and Electroencephalography
Kim, S., Shin, D. Y., Kim, T.-K., Lee, S., Hyun, J. K., & Park, S. (2022) · Sensors · doi:10.3390/s22020680 · Cited by 30
“The CNN algorithm does not extract information from data to learn, but rather extracts the features of data and identifies the patterns of those features [34].”
Background
Accurate Identification Strategy of Coal and Gangue Using Infrared Imaging Technology Combined With Convolutional Neural Network
Hu, F., & Bian, K. (2022) · IEEE Access · doi:10.1109/access.2022.3144386 · Cited by 27
“Recently, deep learning [21], [22], especially convolution neural network (CNN) [23], [24], has become a hot topic in current research and has been widely used in face recognition [25], license plate recognition [26], spectral recognition [27] and other fields.”
Background
Using Convolutional Neural Networks to Efficiently Extract Immense Phenological Data From Community Science Images
Reeb, R. A., Aziz, N., Lapp, S., Kitzes, J. A., Heberling, J. M., & Kuebbing, S. E. (2022) · Frontiers in Plant Science · doi:10.3389/fpls.2021.787407 · Cited by 28
Using a small number of training instances in genetic programming for face image classification
Bi, Y., Xue, B., & Zhang, M. (2022) · Information Sciences · doi:10.1016/j.ins.2022.01.055 · Cited by 30
Evolution of Artificial Intelligence-Powered Technologies in Biomedical Research and Healthcare
Díaz-Flores, E., Meyer, T., & Giorkallos, A. (2022) · Advances in biochemical engineering, biotechnology · doi:10.1007/10_2021_189 · Cited by 29
Simultaneous illumination and imaging based on a single multimode fiber
Ju, Z., Yu, Z., Meng, Z., Zhan, N., Gui, L., & Xu, K. (2022) · Optics Express · doi:10.1364/oe.454850 · Cited by 27
Accurate Recognition of Building Rooftops and Assessment of Long-Term Carbon Emission Reduction from Rooftop Solar Photovoltaic Systems Fusing GF-2 and Multi-Source Data
Lin, S., Zhang, C., Ding, L., Zhang, J., Liu, X., Chen, G., Wang, S., & Chai, J. (2022) · Remote Sensing · doi:10.3390/rs14133144 · Cited by 30
A Survey - Insights of ML and DL in Health Domain
Gandhi, V. C., & Gandhi, P. P. (2022) · International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · doi:10.1109/icscds53736.2022.9760981 · Cited by 27
Convolutional neural networks for ultrasound corrosion profile time series regression
Cantero‐Chinchilla, S., Simpson, C. H., Ballisat, A., Croxford, A. J., & Wilcox, P. D. (2022) · NDT & E International · doi:10.1016/j.ndteint.2022.102756 · Cited by 27
Fault detection using a convolutional neural network trained with point-spread function-convolution-based samples
Jing, J., Yan, Z., Zhang, Z., Gu, H., & Han, B. (2022) · Geophysics · doi:10.1190/geo2021-0824.1 · Cited by 27
Temporally Coherent Backmapping of Molecular Trajectories From Coarse-Grained to Atomistic Resolution
Shmilovich, K., Stieffenhofer, M., Charron, N. E., & Hoffmann, M. (2022) · The Journal of Physical Chemistry A · doi:10.1021/acs.jpca.2c07716 · Cited by 27
A review on street view observations in support of the sustainable development goals
Yin, C., Peng, N., Li, Y., Shi, Y., Yang, S., & Jia, P. (2023) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2023.103205 · Cited by 27
Deep Learning for the Classification of Genomic Signals
Morales, J. A., Saldaña, R., Santana-Castolo, M. H., Torres-Cerna, C. E., Borrayo, E., Mendizabal-Ruiz, A. P., Vélez-Pérez, H. A., & Mendizabal‐Ruiz, G. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/7698590 · Cited by 27
“In particular, the convolutional neural networks (CNN) have become the leading deep learning architecture for most image recognition, classification, and detection tasks [21].”
Background
Application of Spatio-Temporal Context and Convolution Neural Network (CNN) in Grooming Behavior of Bactrocera minax (Diptera: Trypetidae) Detection and Statistics
Zhang, Z., Zhan, W., He, Z., & Zou, Y. (2020) · Insects · doi:10.3390/insects11090565 · Cited by 27
Dataset for "A Bayesian neural network predicts the dissolution of compact planetary systems"
Cranmer, M., & Tamayo, D. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.5501472 · Cited by 33
Survey of Deep Learning Accelerators for Edge and Emerging Computing
Alam, S., Yakopcic, C., Wu, Q., Barnell, M., Khan, S., & Taha, T. M. (2024) · Electronics · doi:10.3390/electronics13152988 · Cited by 38
Automated Detection and Localization of Synaptic Vesicles in Electron Microscopy Images
Imbrosci, B., Schmitz, D., & Orlando, M. (2022) · eNeuro · doi:10.1523/eneuro.0400-20.2021 · Cited by 26
“Thanks to their unique architectures, inspired by the visual cortex, they achieved unpre-ceded results in visual tasks ranging from image classification and object detection to autonomous driving (Rawat and Wang, 2017).”
Background
Automatic determination of pubertal growth spurts based on the cervical vertebral maturation staging using deep convolutional neural networks
Khazaei, M., Mollabashi, V., Khotanlou, H., & Farhadian, M. (2023) · Journal of the World Federation of Orthodontists · doi:10.1016/j.ejwf.2023.02.003 · Cited by 26
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification
Ganj, A., Ebadpour, M., Darvish, M., & Bahador, H. J. (2023) · Iranian Journal of Science and Technology Transactions of Electrical Engineering · doi:10.1007/s40998-023-00618-5 · Cited by 26
In-line particle size measurement during granule fluidization using convolutional neural network-aided process imaging
Péterfi, O., Madarász, L., Ficzere, M., Lestyán-Goda, K., Záhonyi, P., Erdei, G., Sipos, E., Nagy, Z. K., & Galata, D. L. (2023) · European Journal of Pharmaceutical Sciences · doi:10.1016/j.ejps.2023.106563 · Cited by 26
“CNNs are designed to automatically and adaptively learn a large number of filters specific to a training dataset so that highly specific features can be detected anywhere on input images (Khan et al., 2020; Lopez Pinaya et al., 2019; Rawat and Wang, 2017).”
Background
Forest canopy mortality during the 2018-2020 summer drought years in Central Europe: The application of a deep learning approach on aerial images across Luxembourg
Schwarz, S., Werner, C., Fassnacht, F. E., & Ruehr, N. K. (2023) · Forestry An International Journal of Forest Research · doi:10.1093/forestry/cpad049 · Cited by 26
“CNNs are a family of deep learning networks that utilize convolutional layers, which are used to exploit information of spatially adjacent pixels and are therefore very efficient in detecting structural patterns or objects in images (Rawat & Wang 2017).”
Background
Rapid measurement of epidermal thickness in OCT images of skin
Lin, C.-H., Lukas, B., Rajabi‐Estarabadi, A., May, J. R., Pang, Y., Puyana, C., Tsoukas, M. M., & Avanaki, K. (2024) · Scientific Reports · doi:10.1038/s41598-023-47051-6 · Cited by 26
“CNN model structure contains various tunable hyperparameters 23 , such as filter and kernel size and number, pooling size, and type.”
Background
Application of deep learning for the analysis of stomata: a review of current methods and future directions
Gibbs, J. A., & Burgess, A. J. (2024) · Journal of Experimental Botany · doi:10.1093/jxb/erae207 · Cited by 26
Towards Transferable Targeted 3D Adversarial Attack in the Physical World
Huang, Y., Dong, Y., Ruan, S., Yang, X. F., Su, H., & Wei, X. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02314 · Cited by 34
“The surrogate model is ResNet-101 [12] and we can see TT3D shows remarkable transferability. fication [28] and object detection [2, 57], these models are vulnerable to adversarial examples [6, 7, 11, 21, 23, 30, 36, 40, 45–48 , 50].”
Implicit Diversity in Image Summarization
Celis, L. E., & Keswani, V. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415210 · Cited by 32
The Impact of Domain Randomization on Object Detection: A Case Study on Parametric Shapes and Synthetic Textures
Dehban, A., Borrego, J., de Figueiredo, R. P., Moreno, P., Bernardino, A. J. M., & Santos-Victor, J. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968139 · Cited by 26
Recognition of cotton growth period for precise spraying based on convolution neural network
Wang, S., Li, Y., Yuan, J., Song, L., Liu, X., & Liu, X. (2020) · Information Processing in Agriculture · doi:10.1016/j.inpa.2020.05.001 · Cited by 26
Automatic identification of cashmere and wool fibers based on microscopic visual features and residual network model
Luo, J., Lü, K., Chen, Y., & Zhang, B. (2021) · Micron · doi:10.1016/j.micron.2021.103023 · Cited by 26
Training AI-Based Feature Extraction Algorithms, for Micro CT Images, Using Synthesized Data
Konnik, M. T., Ahmadi, B., May, N., Favata, J., Shahbazi, Z., Shahbazmohamadi, S., & Tavousi, P. (2021) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-021-00758-w · Cited by 26
DeepGRAI (Deep Gray Rating via Artificial Intelligence): Fast, feasible, and clinically relevant thalamic atrophy measurement on clinical quality T2-FLAIR MRI in multiple sclerosis
Dwyer, M. G., Lyman, C., Ferrari, H., Bergsland, N., Fuchs, T. A., Jakimovski, D., Schweser, F., Weinstock‐Guttmann, B., Benedict, R. H. B., Riolo, J. V., et al. (2021) · NeuroImage Clinical · doi:10.1016/j.nicl.2021.102652 · Cited by 26
“(Rawat and Wang, 2017) These methods work by training a set of kernels, or filters, to respond to specific features in their input (much like the human visual system includes separate set of neurons responding to horizontal or vertical lines).”
Method
Viscoelastic parameter estimation using simulated shear wave motion and convolutional neural networks
Vasconcelos, L., Kijanka, P., & Urban, M. W. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104382 · Cited by 26
Ensemble deep transfer learning model for Arabic (Indian) handwritten digit recognition
Alkhawaldeh, R. S., Alawida, M., Alshdaifat, N., Alma’aitah, W. Z., & Almasri, A. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06423-7 · Cited by 28
“The training process using these techniques increases time and the computational complexity as they have many layers [36].”
Method
Multitask learning with single gradient step update for task balancing
Lee, S., & Son, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.025 · Cited by 28
CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles’ Machine
Rojas-Dueñas, G., Riba, J., & Moreno‐Eguilaz, M. (2021) · Sensors · doi:10.3390/s21217079 · Cited by 26
“where Ck is obtained from the convolution between the input data x and the feature map Wk, while k refers to the feature map number [35].”
BackgroundMethodInfluential
TripletCough: Cougher Identification and Verification From Contact-Free Smartphone-Based Audio Recordings Using Metric Learning
Jokic, S., Cleres, D., Rassouli, F., Steurer-Stey, C., Puhan, M. A., Brutsche, M. H., Fleisch, E., & Barata, F. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3152944 · Cited by 26
“the domain of computer vision, in particular for image classification, segmentation, and object detection [33].”
Background
STKD: Distilling Knowledge From Synchronous Teaching for Efficient Model Compression
Su, T., Zhang, J., Yu, Z., Wang, G., & Liu, X. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3164264 · Cited by 28
Predicting conversion from MCI to AD by integration of rs-fMRI and clinical information using 3D-convolutional neural network
Ghafoori, S., & Shalbaf, A. (2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02620-4 · Cited by 28
Automatic arrival-time picking of P- and S-waves of microseismic events based on object detection and CNN
Li, J., Li, K., & Tang, S. (2022) · Soil Dynamics and Earthquake Engineering · doi:10.1016/j.soildyn.2022.107560 · Cited by 26
Landslide detection based on shipborne images and deep learning models: a case study in the Three Gorges Reservoir Area in China
Li, Y., Wang, P., Feng, Q., Ji, X., Jin, D., & Gong, J. (2022) · Landslides · doi:10.1007/s10346-022-01997-2 · Cited by 30
“…convolutional neural networks (CNNs), is capable of modeling high-level feature representations through a hierarchical learning framework (Lin et al. 2018; Oquab et al. 2014), which has achieved astonishing performance in many computer-vision tasks, such as image classification (Rawat and Wang.”
Single-frequency and accurate phase unwrapping method using deep learning
Wang, S., Chen, T., Shi, M., Zhu, D., & Wang, J. (2022) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2022.107409 · Cited by 27
An enhanced SSD with feature cross-reinforcement for small-object detection
Gong, L., Huang, X., Chao, Y., Chen, J., & Lei, B. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04544-1 · Cited by 26
Smooth Exploration System: A novel ease-of-use and specialized module for improving exploration of whale optimization algorithm
Wu, L., Chen, E., Guo, Q., Xu, D., Xiao, W., Guo, J., & Zhang, M. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110580 · Cited by 26
MSENet: Mean and standard deviation based ensemble network for cervical cancer detection
Pramanik, R., Banerjee, B., & Sarkar, R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106336 · Cited by 26
Diagnosis of osteoporotic vertebral compression fractures and fracture level detection using multitask learning with U-Net in lumbar spine lateral radiographs
Ryu, S. M., Lee, S., Jang, M., Koh, J., Bae, S. J., Jegal, S. G., Shin, K., & Kim, N. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.06.017 · Cited by 26
“As a result, more layers tend to have higher representational power and can achieve better performance on tasks with large and complex datasets [23,24].”
Background
Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes
Monteiro, R. D. P., Cerrada, M., Cabrera, D. R., Sánchez, R., & Bastos-Filho, C. J. A. (2019) · Computational Intelligence and Neuroscience · doi:10.1155/2019/1383752 · Cited by 26
“*eir basic structure consists of an input layer, alternating blocks of convolutional and pooling layers, which are followed by fully connected layers, and an output layer [16].”
BackgroundMethodInfluential
An object-based and heterogeneous segment filter convolutional neural network for high-resolution remote sensing image classiﬁcation
Pan, X., Zhao, J., & Xu, J. (2019) · International Journal of Remote Sensing · doi:10.1080/01431161.2019.1584687 · Cited by 26
“Convolutional neural networks (CNNs) are feedforward networks whose architecture is inspired by the structure of the visual cortex in the animal brain (Rawat and Wang 2017).”
Background
Potential Predictability of Regional Precipitation and Discharge Extremes Using Synoptic-Scale Climate Information via Machine Learning: An Evaluation for the Eastern Continental United States
Knighton, J. O., Pleiss, G., Carter, E. K., Lyon, S. W., Walter, M. T., & Steinschneider, S. (2019) · Journal of Hydrometeorology · doi:10.1175/jhm-d-18-0196.1 · Cited by 26
“However, NNs are sufficiently flexible in design that they provide a better approximation of the potential predictability of extremes using high-dimensional synoptic-scale climate information, as compared to simpler methods (Rawat and Wang 2017).”
Background
Rapid spatio-temporal prediction of coastal urban floods based on deep learning approaches
Zhang, W., Liu, Y., Tang, W., Chen, S., & Xie, W. (2023) · Urban Climate · doi:10.1016/j.uclim.2023.101716 · Cited by 27
Rapid detection of residual chlorpyrifos and pyrimethanil on fruit surface by surface-enhanced Raman spectroscopy integrated with deep learning approach
Chen, Z., Dong, X., Liu, C., Wang, S., Dong, S., & Huang, Q. (2023) · Scientific Reports · doi:10.1038/s41598-023-45954-y · Cited by 26
“Feature extraction in CNN is realized through the dot product operation between the translation of the convolution kernel on the original data and the corresponding receptor field 26 .”
Method
Prognosis methods of stress corrosion cracking under harsh environmental conditions
Hamdan, H., Alsit, A., Tahhan, A. B. A., Mughieda, O., Mourad, A. I., Shehadeh, M. A., & AlKhedher, M. A. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e25276 · Cited by 28
“…type of deep learning neural network, it is generally used for grid-structured data, which can be images or time-series data, and they have been widely employed in computer vision applications and achieved success in image classification, object detection, and image segmentation applications [194].”
Background
InSAR-YOLOv8 for wide-area landslide detection in InSAR measurements
Ma, R., Yu, H., Liu, X., Yuan, X., Geng, T., & Li, P. (2025) · Scientific Reports · doi:10.1038/s41598-024-84626-3 · Cited by 26
A Learning Approach for Suture Thread Detection With Feature Enhancement and Segmentation for 3-D Shape Reconstruction
Lu, B., Yu, X. B., Lai, J. W., Huang, K., Chan, K. C. C., & Chu, H. K. (2019) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2019.2950005 · Cited by 25
“Compared with common data sets, such as MNIST and CIFAR [41], which require more than 10 000 training images for building an object detection model, the deep-learning”
Method
Surface Classification of Damaged Concrete Using Deep Convolutional Neural Network
Hung, P. D., Su, N. T., & Diep, V. T. (2019) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661819040047 · Cited by 25
Deep multiple instance learning classifies subtissue locations in mass spectrometry images from tissue-level annotations
Guo, D., Föll, M. C., Volkmann, V., Enderle-Ammour, K., Bronsert, P., Schilling, O., & Olga Vitek, A. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa436 · Cited by 25
“CNN convolutes the image using a small-sized kernel to capture the local connectivity within an image (Rawat and Wang, 2017).”
Method
Dealing with Robustness of Convolutional Neural Networks for Image Classification
Arcaini, P., Bombarda, A., Bonfanti, S., & Gargantini, A. (2020) · IEEE International Conference on Artificial Intelligence Testing (AITest) · doi:10.1109/aitest49225.2020.00009 · Cited by 25
Automated Waste Sorting Using Convolutional Neural Network
Huynh, H., Pham-Hoai, P.-T., Tran, A.-K., & Nguyen, T.-D. (2020) · NAFOSTED Conference on Information and Computer Science (NICS) · doi:10.1109/nics51282.2020.9335897 · Cited by 25
“After the first time it was introduced about 40 years ago [17], researchers have been improving the network to enhance the accuracy as well as complexity.”
Background
Application of a convolutional neural network for mooring failure identification
Janas, K., Milne, I. A., & Whelan, J. R. (2021) · Ocean Engineering · doi:10.1016/j.oceaneng.2021.109119 · Cited by 25
Evaluation of Deep Learning against Conventional Limit Equilibrium Methods for Slope Stability Analysis
Azmoon, B., Biniyaz, A., & Liu, Z. “. (2021) · Applied Sciences · doi:10.3390/app11136060 · Cited by 26
Deep fair models for complex data: Graphs labeling and explainable face recognition
Franco, D., Navarin, N., Donini, M., Anguita, D., & Oneto, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.109 · Cited by 26
“This preamble clearly points to the fact that DL is much more effective than classical ML when the input data are complex, or more precisely, structured (e.g., in the form of graphs [42], trees [57], general images [58], or faces [59]).”
Background
Deep Learning Approach for Automatic Microaneurysms Detection
Mateen, M., Malik, T. S., Hayat, S., Hameed, M., Sun, S., & Wen, J. (2022) · Sensors · doi:10.3390/s22020542 · Cited by 25
“Alternatively, deep learning methods, especially the convolutional neural networks (CNNs), are widely used in image classification tasks and have obtained significant results since 2012 [33].”
Method
Current role of endoscopic ultrasound in the diagnosis and management of pancreatic cancer
Salom, F., & Prat, F. (2022) · World Journal of Gastrointestinal Endoscopy · doi:10.4253/wjge.v14.i1.35 · Cited by 27
Distributed memory of neural networks and the problem of the intelligence`s essence
Suleimenov, I. E., Matrassulova, D., Moldakhan, I., Vitulyova, Y. S., Kabdushev, S. B., & Bakirov, A. S. (2022) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v11i1.3463 · Cited by 25
“It is often emphasized that memory of artificial neural networks (ANN) is distributed in current literature [1], [2].”
Mapping discrete fracture networks using inversion of hydraulic tomography data with convolutional neural network: SegNet-Fracture
Vu, M. T., & Jardani, A. (2022) · Journal of Hydrology · doi:10.1016/j.jhydrol.2022.127752 · Cited by 25
Multi-class classification of breast tissue using optical coherence tomography and attenuation imaging combined via deep learning
Foo, K. Y., Newman, K., Fang, Q., Gong, P., Ismail, H. M., Lakhiani, D. D., Zilkens, R., Dessauvagie, B. F., Latham, B. I., Saunders, C. M., et al. (2022) · Biomedical Optics Express · doi:10.1364/boe.455110 · Cited by 25
Unsupervised deep learning of landscape typologies from remote sensing images and other continuous spatial data
van Strien, M. J., & Grêt‐Regamey, A. (2022) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2022.105462 · Cited by 25
Dust InSMS: Intelligent soiling measurement system for dust detection on solar mirrors using computer vision methods
Ydrissi, M. E., Ghennioui, H., Bennouna, E. G., Azouzoute, A., Abraim, M., Taabane, I., & Abdi, F. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118646 · Cited by 27
Nano-porosity effects on corrosion rate of Zr alloys using nanoscale microscopy coupled to machine learning
Zhang, H., Kim, T., Swarts, J., Yu, Z., Su, R., Liu, L., Howland, W., Lucadamo, G. A., & Couet, A. (2022) · Corrosion Science · doi:10.1016/j.corsci.2022.110660 · Cited by 25
An Efficient Convolutional Neural Network with Transfer Learning for Malware Classification
AlGarni, M. D., Alroobaea, R., Almotiri, J., Ullah, S. S., Hussain, S., & Umar, F. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/4841741 · Cited by 27
“Malware has seen an enormous increase in the number of updated versions over the past many years, demonstrating that malware has proven to be successful for the developers [5].”
Background
Early diagnosis of Alzheimer's disease and mild cognitive impairment based on electroencephalography: From the perspective of event related potentials and deep learning
Wang, C., Xu, T., Yu, W., Li, T., Han, H., Zhang, M., & Ming, T. (2022) · International Journal of Psychophysiology · doi:10.1016/j.ijpsycho.2022.10.010 · Cited by 25
A dual branch and fine-grained enhancement network for pancreatic tumor segmentation in contrast enhanced CT images
Zhou, Z., Bian, Y., Pan, S., Meng, Q., Zhu, W., Shi, F., Chen, X., Shao, C., & Xiang, D. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104516 · Cited by 25
Deep Learning-Based Pose Estimation of Apples for Inspection in Logistic Centers Using Single-Perspective Imaging
Giefer, L. A., Castellanos, J. D. A., Babr, M. M., & Freitag, M. (2019) · Processes · doi:10.3390/pr7070424 · Cited by 25
“The use of convolutional neural networks (CNNs) has been revolutionary for image classification tasks; in most cases, the results obtained are more accurate and more accessible to achieve than conventional methods [7].”
Method
Development of internal sound sensor using stethoscope and its applications for machine monitoring
Yun, H., Kim, H., Kim, E., & Jun, M. B. (2020) · Procedia Manufacturing · doi:10.1016/j.promfg.2020.05.147 · Cited by 25
Convolutional neural net face recognition works in non-human-like ways
Hancock, P., Somai, R. S., & Mileva, V. R. (2020) · Royal Society Open Science · doi:10.1098/rsos.200595 · Cited by 25
Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification
Wang, B., Sun, Y., Xue, B., & Zhang, M. (2018) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.26686/wgtn.14273303.v1 · Cited by 225
CVR-Net: A deep convolutional neural network for coronavirus recognition from chest radiography imagesPreprint
Hasan, M. K., Alam, M. A., Elahi, M. T. E., Roy, S., & Wahid, S. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.11993 · Cited by 34
“The deep neural networks, notably the CNNs, are comprehensively applied for image classification or recognition, which have earned powerful performance since 2012 (Rawat and Wang, 2017).”
Background
HybridGCN for protein solubility prediction with adaptive weighting of multiple features
Chen, L., Wu, R., Zhou, F., Zhang, H., & Liu, J. K. (2023) · Journal of Cheminformatics · doi:10.1186/s13321-023-00788-8 · Cited by 25
“Deep learning has demonstrated remarkable success in various domains, including natural language processing [24], image classification [25], and protein engineering [26, 27].”
Background
Deep learning models based on CNN architecture for early keratoconus detection using corneal topographic maps
Kallel, I. F., Mahfoudhi, O., & Kammoun, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17551-8 · Cited by 25
“CNN is also called ConvNet, which is a multilayer neural network [28].”
Computer-aided diagnosis of keratoconus through VAE-augmented images using deep learning
Agharezaei, Z., Firouzi, R., Hassanzadeh, S., Zarei‐Ghanavati, S., Bahaadinbeigy, K., Golabpour, A., Akbarzadeh, R., Agharezaei, L., Bakhshali, M. A., Sedaghat, M. R., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-46903-5 · Cited by 27
Statistical theory for image classification using deep convolutional neural network with cross-entropy loss under the hierarchical max-pooling model
Köhler, M., & Langer, S. (2024) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2024.106188 · Cited by 48
“Deep convolutional neural networks (CNNs) have led to state-of-the-art performance in solving various problems, especially visual recognition tasks, see, e.g., LeCun et al. (2015), Krizhevsky et al. (2012), Schmidhuber (2015), Rawat and Wang (2017).”
Background
Forecasting Bitcoin volatility using machine learning techniques
Huang, Z.-C., Sangiorgi, I., & Urquhart, A. (2024) · Journal of International Financial Markets Institutions and Money · doi:10.1016/j.intfin.2024.102064 · Cited by 38
Filling the drug discovery gap: is high-content screening the missing link?
Dorval, T., Chanrion, B., Cattin, M., & Stephan, J. P. (2018) · Current Opinion in Pharmacology · doi:10.1016/j.coph.2018.07.002 · Cited by 25

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