Convolutional networks and applications in vision
Open accessThe DOI matches its Crossref record; 52 of the 56 references it cites were found in a registry or an index.
Abstract
Intelligent tasks, such as visual perception, auditory perception, and language understanding require the construction of good internal representations of the world (or "features")? which must be invariant to irrelevant variations of the input while, preserving relevant information. A major question for Machine Learning is how to learn such good features automatically. Convolutional Networks (ConvNets) are a biologically-inspired trainable architecture that can learn invariant features. Each stage in a ConvNets is composed of a filter bank, some nonlinearities, and feature pooling layers. With multiple stages, a ConvNet can learn multi-level hierarchies of features. While ConvNets have been successfully deployed in many commercial applications from OCR to video surveillance, they require large amounts of labeled training samples. We describe new unsupervised learning algorithms, and new non-linear stages that allow ConvNets to be trained with very few labeled samples. Applications to visual object recognition and vision navigation for off-road mobile robots are described.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
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
Self-citationDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 3×
“Most common feature extraction systems like SIFT [40], HoG [41] are composed of filterbanks (oriented edge detectors at multiple scales) followed by non-linearities (winner take all) and pooling (histogramming).”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2×
“Most common feature extraction systems like SIFT [40], HoG [41] are composed of filterbanks (oriented edge detectors at multiple scales) followed by non-linearities (winner take all) and pooling (histogramming).”
MethodReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 1×
“The innovation in [5], [1] was to simplify the architecture and to use the back-propagation algorithm to train the entire system in a supervised fashion.”
MethodSelf-citationBeyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916 · cited 4×
“A Pyramid Match Kernel (PMK) SVM [39] classifer can also be seen as another layer of feature extraction since it performs a K-means based feature extraction followed by local histogramming.”
MethodInfluentialGreedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 1×
“Recent research in deep learning [30], [31], [32] has shown that unsupervised learning can be used to train each stage one after the other using only unlabeled data, reducing the requirement for labeled samples significantly.”
Background(1989) · neural information processing systems · Cited by 3,736
Self-citationSparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Best practices for convolutional neural networks applied to visual document analysis
Simard, P. Y., Steinkraus, D., & Platt, J. C. (2005) · Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings. · doi:10.1109/icdar.2003.1227801 · Cited by 2,741
Research works printed but not linked: 4
- lecun, 0, Handwritten digit recognition with a backpropagation network, NIPS'89
- frome, 0, Large-scale privacy protection in street-level imagery, ICCV'09
- collobert, 2008, Torch, Workshop on Machine Learning Open Source Software NIPS
- lecun, 2002, The Lush Reference Manual
Cited by
Items 801–900 of 1,001
CONVOLUTIONAL NEURAL NETWORKS VIA NODE-VARYING GRAPH FILTERS
Gama, F., Leus, G. J. T., Marques, A. G., & Ribeiro, A. (2018) · IEEE Data Science Workshop (DSW) · doi:10.1109/dsw.2018.8439899 · Cited by 26
An extensive review on spectral imaging in biometric systems: Challenges & advancements
Munir, R., & Khan, R. A. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.102660 · Cited by 21
“According to LeCun et al. [157], deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction .”
MethodInfluentialCause identification of electromagnetic transient events using spatiotemporal feature learning
Niazazari, I., Hamidi, R. J., Livani, H., & Arghandeh, R. (2020) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2020.106255 · Cited by 25
Fusing learned representations from Riesz Filters and Deep CNN for lung tissue classification
Joyseeree, R., Otálora, S., Müller, H., & Depeursinge, A. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.06.006 · Cited by 25
“The CNN is the most prominent DL technique for computer vision.”
BackgroundInfluentialClassification of malignancy of lung nodules in CT images using Convolutional Neural Network
da Silva, G., Silva, A. C., de Paiva, A. C., & Gattass, M. (2016) · doi:10.5753/sbcas.2016.9894 · Cited by 25
“Each filter detects a particular feature that occurs in any part of the input [LeCun et al. 2010].”
BackgroundMethodInfluentialPartly Supervised Multi-Task Learning
Imran, A.-A.-Z., Huang, C., Tang, H. N., Fan, W., Yuan, X. H., Hao, D., Qian, Z., & Terzopoulos, D. (2020) · International Conference on Machine Learning and Applications · doi:10.1109/icmla51294.2020.00126 · Cited by 25
“3, the S4MTL model comprises two main components—a segmentation mask generator G and a class discriminator D. Generator G can be any segmentation network, such as U-Net (Ronneberger et al., 2015), and any CNN classifier (LeCun et al., 2010) may be used as discriminator D.”
MethodPengenalan Pola Tulisan Tangan Aksara Arab Menggunakan Metode Convolution Neural Network
Kasim, N., & Nugraha, G. S. (2021) · Jurnal Teknologi Informasi Komputer dan Aplikasinya (JTIKA ) · doi:10.29303/jtika.v3i1.136 · Cited by 25
A study on training fine-tuning of convolutional neural networks
Cai, Z., & Peng, C. (2021) · International Conference on Knowledge and Smart Technology · doi:10.1109/kst51265.2021.9415793 · Cited by 25
“The typical pooling operation includes Maximum Pooling ( MP )and Average Pooling ( AP )[16], [17], [18], [19].”
MethodA Survey on Supervised Convolutional Neural Network and Its Major Applications
Mane, D., & Kulkarni, U. V. (2019) · IGI Global eBooks · doi:10.4018/978-1-7998-0414-7.ch059 · Cited by 25
Feature Learning and Deep Learning Architecture Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_10 · Cited by 25
Machine Learning as a Tool for Hypothesis Generation
Ludwig, J., & Mullainathan, S. (2023) · National Bureau of Economic Research · doi:10.3386/w31017 · Cited by 25
Detection of Concrete Structural Defects Using Impact Echo Based on Deep Networks
Xu, J., & Yu, X. B. (2020) · Journal of Testing and Evaluation · doi:10.1520/jte20190801 · Cited by 24
Artificial intelligence deep learning for 3D IC reliability prediction
Hsu, P.-N., Shie, K.-C., Chen, K.-P., Tu, J.-C., Wu, C., Tsou, N., Lo, Y., Chen, N.-Y., Hsieh, Y.-F., Wu, M., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-08179-z · Cited by 24
Arroni, S., Galán, Y., Guzmán-Guzmán, X., Núñez‐Valdéz, E. R., & Gómez, A. (2023) · International Journal of Interactive Multimedia and Artificial Intelligence · doi:10.9781/ijimai.2023.02.005 · Cited by 24
Wang, L., & Zhang, X. (2023) · Applied Sciences · doi:10.3390/app13095525 · Cited by 24
Modeling transient flow dynamics around a bluff body using deep learning techniques
Li, S., Yang, J., & He, X. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.116880 · Cited by 24
Ponce, P., Balderas, D., Peffer, T. E., & Molina, A. (2017) · Energy and Buildings · doi:10.1016/j.enbuild.2017.12.043 · Cited by 24
Pilia, N., Severi, S., Raimann, J. G., Genovesi, S., Dössel, O., Kotanko, P., Corsi, C., & Loewe, A. (2020) · APL Bioengineering · doi:10.1063/5.0018504 · Cited by 24
Neural networks for classification of strokes in electrical impedance tomography on a 3D head model
Candiani, V., & Santacesaria, M. (2021) · Mathematics in Engineering · doi:10.3934/mine.2022029 · Cited by 24
“r CNN, with two convolutional layers and four fully connected layers. 3.2. Convolutional neural networks. We also consider a convolutional neural network (CNN) for our classication task. We refer to [25] for more details on the architecture of a CNN. As depicted in Figure 3, our network has six layers with weights. Th…”
MethodInfluentialPereira, P. M. M., Thomaz, L. A., Tavora, L. M. N., Assunção, P., Fonseca-Pinto, R., Paiva, R. P., & de Faria, S. M. M. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102254 · Cited by 24
Ke, Z., Liu, X., Chen, Y., Shi, H., & Deng, Z. (2021) · Superconductor Science and Technology · doi:10.1088/1361-6668/ac455d · Cited by 24
“Usually, the input of CNN is an image and it has three dimensions: height, length and depth [44].”
Deep Neural Networks—A Brief History
Cios, K. J. (2017) · Studies in computational intelligence · doi:10.1007/978-3-319-67946-4_7 · Cited by 24
Convolutional adaptive denoising autoencoders for hierarchical feature extraction
Zhang, Q., & Zhang, L. (2018) · Frontiers of Computer Science · doi:10.1007/s11704-016-6107-0 · Cited by 24
“1 Typical CNN structure with seven layers [17] (C1 is the first convolutional layer with N1 feature maps, and S2 is the first subsampling layer)”
BackgroundRuffieux, S., Spycher, N., Mugellini, E., & Khaled, O. A. (2017) · Intelligent Systems Conference (IntelliSys) · doi:10.1109/intellisys.2017.8324359 · Cited by 24
“The proposed architecture of the algorithm has been built upon state-of-the-art architectures for CNN, alternating convolutional and pooling layers [24].”
MethodMulti-path Convolutional Neural Networks for Complex Image ClassificationPreprint
Wang, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.04701 · Cited by 24
“Convolutional Neural Networks [6],[10],[11],[12],[20] show significant advantages on image classification tasks.”
BackgroundJasper, C. E., Dyer, B. C., Reilly, B. T., Williams, T., Hemming, S. R., & Raymo, M. E. (2024) · Paleoceanography and Paleoclimatology · doi:10.1029/2024pa004897 · Cited by 23
Arsoniadis, C. G., & Nikolaidis, V. C. (2024) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2024.101551 · Cited by 24
Ghanbari, H., & Antoniades, D. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102906 · Cited by 23
Li, G., Gu, X., Ren, Z., Wu, Q., Liu, X., Zhang, L., Xiao, D., & Zhou, C. (2022) · Minerals · doi:10.3390/min12081012 · Cited by 23
Computer-aided diagnostic system for hypertensive retinopathy: A review
Suman, S., Tiwari, A. K., & Singh, K. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107627 · Cited by 23
Attention-Based Semantic Segmentation Networks for Forest Applications
Lim, S. V., Zulkifley, M. A., Saleh, A., Saputro, A. H., & Abdani, S. R. (2023) · Forests · doi:10.3390/f14122437 · Cited by 23
“A CNN is a popular deep learning model used for image processing and object detection, and it has multiple hidden layers [10,13].”
BackgroundAdvancing electron microscopy using deep learning
Chen, K., & Barnard, A. S. (2024) · Journal of Physics Materials · doi:10.1088/2515-7639/ad229b · Cited by 23
Mirror Symmetry Histograms for Capturing Geometric Properties in Images
Cicconet, M., Geiger, D., Gunsalus, K. C., & Werman, M. (2014) · 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/cvpr.2014.381 · Cited by 23
“Recently, there has been great advance in building computational representations of more complex objects via so-called Deep Learning methods [3, 10, 13], where the basic idea is to perform convolutions with filters and pooling coefficients from the convolution outputs.”
BackgroundFusing Multilabel Deep Networks for Facial Action Unit Detection
Bishay, M., & Patras, I. (2017) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2017.86 · Cited by 23
“Each CNN consists of 3 convolutional layers and 1 fully connected layer, each convolutional layer is followed by a maxpooling layer [19].”
Image classification using label constrained sparse coding
Liu, R., Chen, Y., Zhu, X., & Hou, K. (2015) · Multimedia Tools and Applications · doi:10.1007/s11042-015-2626-1 · Cited by 23
“[22] proposed the convolutional networks with good performance for automatic learning while Fan et al.”
BackgroundMethodExploring Automated Pottery Identification [Arch-I-Scan]
Tyukin, I., Sofeikov, K., Levesley, J., Gorban, A. N., Allison, P. M., & Cooper, N. J. (2018) · Internet Archaeology · doi:10.11141/ia.50.11 · Cited by 23
Classification of Error Related Potentials using Convolutional Neural Networks
Swamy Bellary, S. A., & Conrad, J. M. (2019) · 2019 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence.2019.8776901 · Cited by 21
“ConvNets have been very successful in numerous tasks such as image classification [17], speech recognition [18].”
MethodA CNN-Based CMP Planarization Model Considering LDE Effect
Bao, H., & Chen, L. (2020) · IEEE Transactions on Components Packaging and Manufacturing Technology · doi:10.1109/tcpmt.2020.2979472 · Cited by 23
Aloyayri, A., & Krzyżak, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61401-0_45 · Cited by 23
“2 A typical ConvNet architecture with two feature stages (Extracted from [45]).”
BackgroundArjunagi, S., & Patil, N. (2021) · International Journal of Information Technology · doi:10.1007/s41870-021-00657-3 · Cited by 23
Hyunha, N. A. M., & Sugiyama, M. (2015) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2014edp7335 · Cited by 23
“All the model parameters such as the size of the convolution mask, the number of layers and learning rate are tuned in the same way as the previous studies [26], [27].”
ResultChen, X., Chen, Q., Tian, M., Ji, M., Zou, C., Wang, X., & Wang, B. (2017) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads.2017.00034 · Cited by 23
“A general CNN model is composed of several layers, including Conv layers, FC layers, Pooling layers, Nonlinearity layers, which are connected as a directed acyclic graph [27].”
MethodA Convolutional Neural Network for Pedestrian Gender Recognition
Ng, C.-B., Tay, Y. H., & Goi, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39065-4_67 · Cited by 23
Real-Time Neural Classifiers for Sensor Faults in Three Phase Induction Motors
Sánchez, O. D., Martínez-Soltero, G., Alvarez, J. G., & Alanís, A. Y. (2023) · IEEE Access · doi:10.1109/access.2023.3246379 · Cited by 22
“CNN is formed by three layers in each stage: a filter bank layer, a non-linearity layer and a feature grouping layer [46].”
Sebastian, A. E., & Dua, D. (2023) · Sensing and Imaging · doi:10.1007/s11220-022-00406-1 · Cited by 22
Alshamrani, A. F. A., & Alshomrani, F. (2024) · IEEE Access · doi:10.1109/access.2024.3524633 · Cited by 22
EEG_GLT-Net: Optimising EEG graphs for real-time motor imagery signals classification
Aung, H. W., Li, J. J., Shi, B., An, Y., & Su, S. W. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107458 · Cited by 24
A Comparison: Different DCNN Models for Intelligent Object Detection in Remote Sensing Images
Ding, P., Zhang, Y., Jia, P., & Chang, X. (2018) · Neural Processing Letters · doi:10.1007/s11063-018-9878-5 · Cited by 22
“Convolutional neural networks including convolution layers and feature pooling layers and fully connected layers [15].”
Backgroundde Lima, L. L., Ferreira, J. R., & Oliveira, M. C. (2020) · Computational Intelligence · doi:10.1111/coin.12350 · Cited by 22
“12,13 19-22 According to LeCun et al, 23 DL methods are representation-learning methods with multiple levels of representation, obtained by composing simple but nonlinear modules that each transform the representation at one level into F I G U R E 1 Examples of small lung nodules (highlighted in…”
Neural Simpletrons: Learning in the Limit of Few Labels with Directed Generative Networks
Forster, D., Sheikh, A.-S., & Lücke, J. (2018) · Neural Computation · doi:10.1162/neco_a_01100 · Cited by 22
“volved over the last decade, with significant progress on both the modeling and the application side. Important standard models are Deep Belief Networks (DBN; [1]), convolutional neural networks (CNN; [2, 3]), Deep Boltzmann Machines (DBM, [4]) or deep autoencoders (e.g.[5]). The often hybrid use of unsupervised and su…”
BackgroundDeep neural network-aided coherent integration method for maneuvering target detection
Wang, C., Zheng, J., Jiu, B., Liu, H., & Shi, Y. (2021) · Signal Processing · doi:10.1016/j.sigpro.2021.107966 · Cited by 22
Observer Dependent Lossy Image Compression
Weber, M., Renggli, C., Gräbner, H., & Zhang, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-71278-5_10 · Cited by 22
“Features learned by convolutional neural networks [26] for image classification provide a promising alternative.”
Facial Expression Recognition Using CNN with Keras
Khopkar, A. (2021) · Bioscience Biotechnology Research Communications · doi:10.21786/bbrc/14.5/10 · Cited by 22
Yuan, X., Tanksley, D., Jiao, P., Li, L., Chen, G., & Wunsch, D. C. (2021) · Frontiers in Built Environment · doi:10.3389/fbuil.2021.660103 · Cited by 22
Mistree, K., Thakor, D., & Bhatt, B. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120881 · Cited by 22
“CNN architecture is selected for our work as it is best suited for capturing internal representation of features of visual world [42].”
MethodHierarchical Data Classification Using Deep Neural Networks
Tirumala, S. S., & Narayanan, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26532-2_54 · Cited by 22
“Since then DNNs became increasingly successful with applications in natural language processing [4] [5], image recognition [6] [7] [8], visual recognition [9], computer vision [10] [11], text mining [12] and hand-written character recognition [13].”
BackgroundHandwritten Isolated Bangla Compound Character Recognition
Fardous, A., & Afroge, S. (2019) · International Conference on Electrical, Computer and Communication Engineering · doi:10.1109/ecace.2019.8679258 · Cited by 22
“VI. CONCLUSION AND FUTURE WORKS In this paper, a CNN based model has been demonstrated which shows significant improvement over already devised classification methods for recognizing handwritten compound Bangla characters.”
MethodInfluentialArik, S., Huang, T., Lai, W. K., & Liu, Q. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26555-1 · Cited by 22
Yin, F., Lin, Z., Xu, Y., Kong, Q., Li, D., Theodoridis, S., Shuguang, & Cui (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03697 · Cited by 22
Activation Space Selectable Kolmogorov-Arnold NetworksPreprint
Yang, Z., Zhang, J., Luo, X., Lu, Z., & Shen, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.08338 · Cited by 22
“In the broad AI paradigm, almost all feature extractors have adopted the concept of the perceptron, such as CNN (LeCun, Kavukcuoglu, and Farabet 2010; Liu et al. 2022; Ding et al. 2022), SNN (Lindblad, Kinser, and Taylor 2005; Tavanaei et al. 2019; Yao et al. 2023), recurrent neural networks (RNN)…”
BackgroundFoundations and Advances in Deep Learning
Cho, K. (2014) · Aaltodoc (Aalto University) · Cited by 23
End-to-End Neural Video Compression: A Review
Gomes, J. S., Grellert, M., Ramos, F. L. L., & Bampi, S. (2025) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2025.3559774 · Cited by 23
“CNNs are a feedforward network that adopts the convolution operation to characterize the correlation between neighboring pixels in images, learning features via optimizing filters (kernels) [25].”
Hyperdrive: A Systolically Scalable Binary-Weight CNN Inference Engine for mW IoT End-Nodes
Andri, R., Cavigelli, L., Rossi, D., & Benini, L. (2018) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi.2018.00099 · Cited by 21
Machine learning based data retrieval for inverse scattering problems with incomplete data
Gao, Y. H., & Zhang, K. (2020) · Journal of Inverse and Ill-Posed Problems · doi:10.1515/jiip-2019-0101 · Cited by 21
“It became popular and widely accepted around 2010 due to the development of efficient learning algorithms [25, 26, 35, 37, 38] and hardware speed-ups such as the use of GPUs.”
BackgroundLin, Z., Zhu, F., Wang, Q., Kong, Y., Wang, J., Huang, L. P., & Hao, Y. (2022) · Remote Sensing · doi:10.3390/rs14133118 · Cited by 21
Improved Manual Annotation of EEG Signals through Convolutional Neural Network Guidance
Diachenko, M., Houtman, S. J., Juárez-Martinez, E. L., Ramautar, J. R., Weiler, R., Mansvelder, H. D., Bruining, H., Bloem, P., & Linkenkaer‐Hansen, K. (2022) · eNeuro · doi:10.1523/eneuro.0160-22.2022 · Cited by 21
“For example, because of hierarchical feature learning, convolutional neural networks (CNNs; LeCun et al., 1989, 1998, 2010, 2015) can recognize complex patterns from minimally preprocessed data.”
BackgroundClassification of Lung Chest X-Ray Images Using Deep Learning with Efficient Optimizers
Asaithambi, A., & Thamilarasi, V. (2023) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc57344.2023.10099228 · Cited by 21
Venkatesh, K., & Naik, K. J. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03094-4 · Cited by 21
“This CNN was introduced by [32].”
Real-time 3D tracking of swimming microbes using digital holographic microscopy and deep learning
Matthews, S. A., Coelho, C., Salas, E. E. R., Brock, E. E., Hodge, J., Walker, J. A., & Wilson, L. G. (2024) · PLoS ONE · doi:10.1371/journal.pone.0301182 · Cited by 21
Object Detection Using Convolutional Neural Networks: A Comprehensive Review
Issaoui, H., ElAdel, A., & Zaied, M. (2024) · IEEE International Symposium on Real-Time Distributed Computing (ISORC) · doi:10.1109/isorc61049.2024.10551342 · Cited by 21
Multimodal architecture for emotion in robots using deep learning
Ghayoumi, M., & Bansal, A. K. (2016) · Future Technologies Conference · doi:10.1109/ftc.2016.7821710 · Cited by 21
“in [12], [8], is the most popular deep neural network model in use for computer vision problems.”
BackgroundBlind Quality Estimation by Disentangling Perceptual and Noisy Features in High Dynamic Range Images
Kottayil, N. K., Valenzise, G., Dufaux, F., & Cheng, I. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2778570 · Cited by 21
“neural networks([8]); hence there are no issues with the convergence.”
BackgroundRetrieval of Hyperspectral Surface Reflectance Based on Machine Learning
Zhu, S., Lei, B., & Wu, Y. (2018) · Remote Sensing · doi:10.3390/rs10020323 · Cited by 21
“For supervised learning, support vector machine (SVM) [11] and convolutional neural networks (CNNs) [12,13] perform best on most typical datasets, including MNIST [14] (an open database of handwritten digits) and ImageNet [15] (a widely used open dataset for image classification).”
MethodAn Indoor Room Classification System for Social Robots via Integration of CNN and ECOC
Othman, K. M., & Rad, A. B. (2019) · Applied Sciences · doi:10.3390/app9030470 · Cited by 21
“Second, CNN considers the spatial structure of the image by translating inputs to outputs through shared filters [22].”
BackgroundLee, D., Kim, H., Choi, B., & Kim, H.-J. (2019) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ab1cee · Cited by 21
“Two typical techniques, including gradient descent and backpropagation algorithms, are used for the process of training deep learning (LeCun et al 2010, 2015, Lee et al 2019).”
MethodEnhancing Local Feature Extraction with Global Representation for Neural Text Classification
Niu, G., Xu, H., He, B., Xiao, X., Wu, H. R., & Gao, S. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1047 · Cited by 21
“Convolutional Neural Networks (CNN) (LeCun et al., 2010) are promising methods for their strong capacities in capturing local invariant regularities (Kim, 2014).”
BackgroundMethodClassifying functional nuclear images with convolutional neural networks: a survey
Lin, Q., Man, Z., Cao, Y., Deng, T., Han, C., Cao, C., Zhang, L., Zeng, S., Gao, R., Wang, W., et al. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1690 · Cited by 21
“In this way, the input can be invariant to geometrical distortions [28, 47].”
BackgroundOutput-based adaptive aerodynamic simulations using convolutional neural networks
Chen, G., & Fidkowski, K. J. (2021) · Computers & Fluids · doi:10.1016/j.compfluid.2021.104947 · Cited by 21
“A traditional CNN uses nonlinear activation after the pooling layer while modern models often do not [55].”
MethodAn Empirical Experiment on Deep Learning Models for Predicting Traffic Data
Lee, H., Park, C., Jin, S., Chu, H., Choo, J., & Ko, S. (2021) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde51399.2021.00160 · Cited by 21
“CNN [27] Simple architecture Good at local feature extraction Prediction for multiple steps at once Should find the best filter size STGCN, ASTGCN, Graph-WaveNet”
WAMS-based two-level robust detection methodology of power system events
Lopes, G. V. D. S., Moraes, G. R., Issicaba, D., & Dotta, D. (2022) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2022.100689 · Cited by 21
PSO-Convolutional Neural Networks With Heterogeneous Learning Rate
Phong, N. H., Santos, A., & Ribeiro, B. (2022) · IEEE Access · doi:10.1109/access.2022.3201142 · Cited by 21
“Illustration of a traditional ConvNet design [22].”
BackgroundWen, F., Li, Z., Wan, C., Su, L., Zhao, Z., Zeng, J., Wang, S., & Pan, B. (2022) · Physics of Fluids · doi:10.1063/5.0132105 · Cited by 21
A neuromorphic system for video object recognition
Khosla, D., Chen, Y., & Kim, K. (2014) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2014.00147 · Cited by 21
“The entire network can be trained using backpropagation with stochastic gradient descent (LeCun et al., 2010).”
BackgroundMethodInfluentialYu, Y., Liu, F., & Mao, S. (2018) · Neural Processing Letters · doi:10.1007/s11063-018-9800-1 · Cited by 21
Document Image Retrieval Using Deep Features
Wiggers, K. L., Britto, A. S., Heutte, L., Koerich, A. L., & Oliveira, L. S. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489722 · Cited by 21
“Equation 1 shows the output of the feature map h obtained by an activation function f [27].”
BackgroundDeep Leaning-Based Approach for Mental Workload Discrimination from Multi-channel fNIRS
Ho, T. K. K., Gwak, J., Park, C. M., Khare, A., & Song, J.-I. (2018) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-2685-1_41 · Cited by 21
Understanding Spectral Graph Neural NetworkPreprint
Chen, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.06660 · Cited by 22
“The graph neural network is motivated by CNNs which have been successfully applied in the field of computer vision [36, 35, 64, 13].”
MethodBrain Tumor Detection and Classification using Convolution Neural NetworkPreprint
Manjunath, S., B, S. P. M., N, D. R. B., & K, M. M. G. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3507904 · Cited by 21
Spectral classification using convolutional neural networksPreprint
Hála, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.8341 · Cited by 21
“1: Example of a two stage convolutional neural network [29].”
BackgroundMethodInfluentialIce concentration estimation in the gulf of St. Lawrence using fully convolutional neural network
Wang, L., Scott, K. A., Clausi, D. A., & Xu, Y. L. (2017) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2017.8128124 · Cited by 20
“CNNs were originally designed for image labeling tasks, which require one label for one target image [5, 4].”
BackgroundMethodLargent, A., Asis‐Cruz, J. D., Kapse, K. J., Barnett, S. D., Murnick, J., Basu, S., Andersen, N., Norman, S., Andescavage, N. N., & Limperopoulos, C. (2022) · Human Brain Mapping · doi:10.1002/hbm.25762 · Cited by 20
Montalbo, F. J. P. (2022) · Machine Vision and Applications · doi:10.1007/s00138-022-01277-y · Cited by 20
“1 College of Informatics and Computing Science, Batangas State University, Rizal Ave, Extension, Batangas, 4200 Batangas City, Philippines [4].”
BackgroundXu, Y., & Zuo, R. (2024) · Mathematical Geosciences · doi:10.1007/s11004-024-10158-1 · Cited by 20
“The convolution operation can be mathematically expressed as (Lecun et al. 2010) where A ( t ) is the value of the output feature at position t , X represents the input data features, W is the filter (kernel) applied to the input, b is the bias term, and m is the filter size.”
Wei, Q., & Wang, W. (2017) · IOP Conference Series Earth and Environmental Science · doi:10.1088/1755-1315/69/1/012156 · Cited by 20
“…deep convolutional neural network is a complete image, from the processing of the hidden layer to the full connection layer, the full connection layer is similar to [7,8,9] is based on neural network, so it includes the basic structure of neural network, input layer, hidden layer and output layer.”
BackgroundIndoor Home Scene Recognition Using Capsule Neural Networks
Basu, A., Petropoulakis, L., Caterina, G. D., & Soraghan, J. J. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.03.253 · Cited by 20
In Situ Learning in Hardware Compatible Multilayer Memristive Spiking Neural Network
Li, J., Xu, H., Sun, S., Li, N., Li, Q., Li, Z., & Liu, H. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2021.3049487 · Cited by 20
“Various types of artificial neural networks (ANNs) are designed for specific applications, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs) [2], [3].”
BackgroundPolat, H., Özerdem, M. S., Ekici, F., & Akpolat, V. (2021) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22558 · Cited by 20
“32 The mathematical expression of the operations carried out in the convolutional layer is given as follows; where the input image given to the convolutional layer is the w JxI dimension convolutional kernel, b is bias, and y is the feature map resulting from convolutional.”
MethodTsai, A. (2021) · Pediatric Radiology · doi:10.1007/s00247-021-05004-z · Cited by 20
A deep learning approach to automatically quantify lower extremity alignment in children
Tsai, A. (2021) · Skeletal Radiology · doi:10.1007/s00256-021-03844-2 · Cited by 20
Patil, A. T., Acharya, R., Patil, H. A., & Guido, R. C. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101281 · Cited by 21
Metadata
- Authors
- LeCun, Y., Kavukcuoglu, K., & Farabet, C.
- Affiliations
- Courant Institute of Mathematical Sciences (US)
- ORCID
- LeCun, Yann
- Venue
- Proceedings of 2010 IEEE International Symposium on Circuits and Systems
- Publisher
- IEEE
- Published
- 2010-05
- Pages
- 253-256
- ISSN
- 0271-4302 (ISSN-L)
- OpenAlex
- W2015861736
- Semantic Scholar
- c43025c429b1fbf6f1379f61801a1b40834d62e7
- Cited by
- 2,213
- References
- 56
- Citations by year
- 2026: 30 · 2025: 112 · 2024: 168 · 2023: 201 · 2022: 223 · 2021: 242 · 2020: 255 · 2019: 240 · 2018: 206 · 2017: 183 · 2016: 142 · 2015: 94 · 2014: 59 · 2013: 21 · 2012: 21
- FWCI
- 15.63
- Type
- conference paper
- Language
- en
- Open access
- green
- hal.science
- Licence
- other-oa
- Locations
- IEEE International Symposium on Circuits and Systems proceedings (publishedVersion)
- HAL (submittedVersion, other-oa)
- 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, unsupervised learning, representation learning, hierarchical feature representation, filter banks, feature pooling, nonlinear activation functions, visual object recognition, visual navigation, mobile robots, few labeled samples
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.