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 401–500 of 1,001
Nogueira, R. F., Lotufo, R. D. A., & Machado, R. C. (2014) · IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BIOMS) · doi:10.1109/bioms.2014.6951531 · Cited by 70
“Although the filter weights can be learned, as described in [28], filters with random weights can perform well and they have the advantage that they do not need to be learned [29] [30] [31].”
BackgroundA Deep Convolution Neural Network Model for Vehicle Recognition and Face Recognition
Luo, X., Shen, R., Hu, J., Deng, J., Hu, L., & Guan, Q. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.03.153 · Cited by 70
Retina blood vessel segmentation using a U-net based Convolutional neural network
Xiancheng, W., Wei, L., Bingyi, M., He, J., Jiang, Z., Xu, W., Ji, Z., Hong, G., & Zhaomeng, S. (2018) · Swinburne figshare (Swinburne University of Technology) · doi:10.25916/sut.26248415 · Cited by 70
Comparing ensemble strategies for deep learning: An application to facial expression recognition
Renda, A., Barsacchi, M., Bechini, A., & Marcelloni, F. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.06.025 · Cited by 70
Tolerating Soft Errors in Deep Learning Accelerators with Reliable On-Chip Memory Designs
Azizimazreah, A., Gu, Y., Gu, X., & Chen, L. (2018) · 2018 IEEE International Conference on Networking, Architecture and Storage (NAS) · doi:10.1109/nas.2018.8515692 · Cited by 56
Weyts, K., Lasnon, C., Ciappuccini, R., Lequesne, J., Corroyer‐Dulmont, A., Quak, E., Clarisse, B., Roussel, L., Bardet, S., & Jaudet, C. (2022) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-022-05800-1 · Cited by 69
“The algorithm is based on deep convolutional neural networks (DCNN), the most common DL architecture [23, 24].”
MethodBhakta, I., Phadikar, S., Majumder, K., Mukherjee, H., & Sau, A. (2022) · Precision Agriculture · doi:10.1007/s11119-022-09927-x · Cited by 69
Zuo, R., & Xu, Y. (2023) · Computers & Geosciences · doi:10.1016/j.cageo.2023.105490 · Cited by 69
Brain MRI segmentation with patch-based CNN approach
Cui, Z., Yang, J., & Qiao, Y. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554465 · Cited by 68
Large-scale offline signature recognition via deep neural networks and feature embedding
Çalık, N., Kurban, O. C., Yilmaz, A. R., Yıldırım, T., & Durak-Ata, L. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.03.027 · Cited by 69
Towards closing the energy gap between HOG and CNN features for embedded vision
Suleiman, A., Chen, Y., Emer, J., & Sze, V. (2017) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2017.8050341 · Cited by 68
“In contrast, learned features learn a representation with the desired characteristics directly from data using deep convolutional neural networks (CNNs) [4].”
BackgroundA deep learning classifier for sentence classification in biomedical and computer science abstracts
Gonçalves, S., Cortez, P. C., & Moro, S. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04334-2 · Cited by 68
“The purpose of the convolutional layers is to extract features that preserve relevant information from the inputs [33].”
BackgroundNoise invariant partial discharge classification based on convolutional neural network
Raymond, W. J. K., Xin, C. W., Kin, L. W., & Illias, H. A. (2021) · Measurement · doi:10.1016/j.measurement.2021.109220 · Cited by 67
Machine-Learning-Based Leakage-Event Identification for Smart Water Supply Systems
Zhou, B., Lau, V. K. N., & Wang, X. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2958920 · Cited by 68
“…addition, we consider the ML-based LI methods (trained using the SGD algo-rithm) with the conventional maximum and average pooling approaches [25], [26], respectively, as baseline methods for comparison with our proposed ML-based LI solution (trained by our novel FuSO algorithm) using our novel…”
MethodMedical Prescription Recognition using Machine Learning
Hassan, E., Tarek, H., Hazem, M., Bahnacy, S., Shaheen, L., & Elashmwai, W. H. (2021) · IEEE Annual Computing and Communication Workshop and Conference (CCWC) · doi:10.1109/ccwc51732.2021.9376141 · Cited by 66
“…nor so successfully and sufficiently as most of the apps or approaches used Optical Character Recognition (OCR) technique and other techniques [5][6][7][8][9] which solved the problem but not completely as OCR at some point cannot fully recognize characters written in bad handwriting or bad format.”
New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis
Amrani, M., Bey, A., & Amamra, A. (2021) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.1953719 · Cited by 66
COVID-19 detection with traditional and deep features on cough acoustic signals
Erdoğan, Y. E., & Narin, A. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104765 · Cited by 66
Yu, X., & Li, D. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3351755 · Cited by 66
“Convolutional neural network (CNN) layers generate multiple output feature maps through convolutions between the same input feature map and multiple kernels [26].”
BackgroundMethodZhang, W., Zhang, C., Zhao, Y., Wang, Z., Liu, Y., Zhou, C., & Hu, Y. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.115020 · Cited by 66
Large-Scale Weakly Supervised Object Localization via Latent Category Learning
Wang, C., Huang, K., Ren, W., Zhang, J., & Maybank, S. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2396361 · Cited by 54
“In recent years, with the great progress in theoretical achievements and parallel computing, the deep neural networks have achieved great success in many large-scale visual tasks [48]–[50].”
BackgroundDeprivation pockets through the lens of convolutional neural networks
Wang, J., Kuffer, M., Roy, D., & Pfeffer, K. (2019) · Remote Sensing of Environment · doi:10.1016/j.rse.2019.111448 · Cited by 66
Deep unsupervised network for multimodal perception, representation and classification
Droniou, A., Ivaldi, S., & Sigaud, O. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.11.005 · Cited by 65
Combined scattering for rotation invariant texture analysis.
Sifre, L., & Mallat, S. (2012) · The European Symposium on Artificial Neural Networks · Cited by 65
Complex-valued convolutional neural networks for real-valued image classification
Popa, C.-A. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7965936 · Cited by 65
“Although they had many applications in computer vision [4], convolutional networks started gaining more popularity only with the increase in the available computational resources and their implementation using parallel computing on graphics processors (GPU).”
BackgroundUnderstanding convolutional neural networks using a minimal model for handwritten digit recognition
Teow, M. Y. W. (2017) · IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS) · doi:10.1109/i2cacis.2017.8239052 · Cited by 65
“After the success of AlexNet, VGG, GoogLeNet, and ResNet in ImageNet image classification challenge, CNNs became an important technique for computer vision researchers to design more effective and sophisticated visual recognition applications [5].”
BackgroundMethodInfluentialApostolopoulos, I. D., Apostolopoulos, D. I., Spyridonidis, T., Papathanasiou, N. D., & Panayiotakis, G. (2021) · Physica Medica · doi:10.1016/j.ejmp.2021.04.011 · Cited by 65
Yi, D., Su, J., & Chen, W. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.072 · Cited by 65
“This is because deep CNNs are powerful in feature extraction and representation [23].”
BackgroundA review on the recent applications of deep learning in predictive drug toxicological studies
Sinha, K., Ghosh, N., & Sil, P. C. (2023) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.2c00375 · Cited by 64
Designing Hardware for Machine Learning: The Important Role Played by Circuit Designers
Sze, V. (2017) · IEEE Solid-State Circuits Magazine · doi:10.1109/mssc.2017.2745798 · Cited by 64
“For computer vision applications, DNNs are often composed of mult iple con volutional (CONV) layers [13] as shown in Figure 3; each layer involves the application of multiple high dimensional filters to the incoming data.”
MethodIdentifying tweets of personal health experience through word embedding and LSTM neural network
Jiang, K., Feng, S., Song, Q., Calix, R. A., Gupta, M., & Bernard, G. R. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2198-y · Cited by 63
“Inspired by the recent advancement in achieving high accuracies in recognizing objects from images using raw image data along with deep neural networks [16, 17], we designed an approach that explores the usage of raw tweet textual data as input to the deep neural network-based classifier.”
BackgroundUsing Multi-level Convolutional Neural Network for Classification of Lung Nodules on CT images
Lyu, J., & Ling, S. H. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512376 · Cited by 63
Convolutional Neural Networks for On-Street Parking Space Detection in Urban Networks
Gkolias, K., & Vlahogianni, E. I. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2882439 · Cited by 66
“The training of convolutional networks is usually based on stochastic gradient descent method [24].”
BackgroundMethodSurvey on Deep Learning Techniques for Person Re-Identification TaskPreprint
Lavi, B., Serj, M. F., & Ullah, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.05284 · Cited by 63
“Inspired by great success of convolutional neural networks (CNNs) [8] in the area of CV [9, 10], it is therefore adopted by researchers for PReID tasks.”
MethodProceedings of the First Workshop on Abusive Language Online
(2017) · doi:10.18653/v1/w17-30 · Cited by 62
Zhang, R., Guo, Z., Sun, Y., Lu, Q., Xu, Z., Yao, Z., Duan, M., Liu, S., Ren, Y., Huang, L., et al. (2020) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-020-00393-5 · Cited by 62
“The convolutional layer utilizes the convolutional kernel to extract local features from the training images, such as extracting features in the human vision system [19].”
MethodFan, Z., Wu, X., Li, C., Chen, H., Liu, W., Zheng, Y., Chen, J., Li, X., Sun, H., Jiang, T., et al. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107070 · Cited by 62
Joint time-frequency scattering for audio classification
Andén, J., Lostanlen, V., & Mallat, S. (2015) · Machine learning for signal processing ... · doi:10.1109/mlsp.2015.7324385 · Cited by 62
“The cascade structure of alternating convolutions and modulus nonlinearities is also shared by convolutional neural networks, which enjoy significant success in many classification tasks [6, 7].”
BackgroundLee, D., Choi, S., & Kim, H. (2018) · Medical Physics · doi:10.1002/mp.13258 · Cited by 64
“21,22 Training proceeds so that the gradient value of the loss function for each parameter ( D L/ D h k ) obtained by backpropagation is to be descending.”
BackgroundDual Deep Learning Model for Image Based Smoke Detection
Pundir, A. S., & Raman, B. (2019) · Fire Technology · doi:10.1007/s10694-019-00872-2 · Cited by 62
“Deep CNN has shown its dominance triumph in many classification problems for extraction of features [4, 29, 30, 32].”
BackgroundBangla handwritten character recognition using deep belief network
Sazal, M. M. R., Biswas, S. K., Amin, M. F., & Murase, K. (2014) · International Conference on Electrical Information and Communication Technology (EICT) · doi:10.1109/eict.2014.6777907 · Cited by 61
“Another technique that extracts local features is the convolutional neural network [13], [14].”
MethodHo, T. K. K., Gwak, J., Park, C. M., & Song, J. (2019) · IEEE Access · doi:10.1109/access.2019.2900127 · Cited by 61
“Meanwhile, CNN variants [11], [12] have recently emerged as robust supervised technique, successfully applied in EEG sleep stage scoring [13] in combination of convolution layers and pooling layers.”
MethodA Geometry-Inspired Decision-Based Attack
Liu, Y., Moosavi-Dezfooli, S.-M., & Frossard, P. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00499 · Cited by 62
“Deep neural networks have led to major breakthroughs in recent years and have been developing as powerful tools in various applications, including computer vision [15, 14], speech [19, 11], health-care [13, 17], etc.”
BackgroundBlancard, B. R.-S., Levrier, F., Allys, E., Bellomi, E., & Boulanger, F. (2020) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202038044 · Cited by 61
Deep learning based automatic segmentation of metastasis hotspots in thorax bone SPECT images
Lin, Q., Luo, M., Gao, R., Li, T., Man, Z., Cao, Y., & Wang, H. (2020) · PLoS ONE · doi:10.1371/journal.pone.0243253 · Cited by 61
“Marvelous innovations in deep learning have promoted a variety of popular deep architectures, ranging from the convolutional neural networks (CNNs) [31], recurrent neural networks (RNNs) [32] and deep belief networks (DBNs) [33] to generative adversarial networks (GANs) [34].”
BackgroundDeep learning based automated diagnosis of bone metastases with SPECT thoracic bone images
Lin, Q., Li, T., Cao, C., Cao, Y., Man, Z., & Wang, H. (2021) · Scientific Reports · doi:10.1038/s41598-021-83083-6 · Cited by 61
“A number of deep architectures are available, such as the convolutional neural networks (CNNs) 21 , recurrent neural networks (RNNs) 22 , and deep belief networks (DBNs) 23 as well as generative adversarial networks (GANs) 24 .”
BackgroundVisual privacy attacks and defenses in deep learning: a survey
Zhang, G., Liu, B., Zhu, T., Zhou, A., & Zhou, W. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10123-y · Cited by 60
“Convolutional neural networks (CNNs) are widely used in deep learning, which can extract representations from input data (LeCun et al. 2010).”
BackgroundFine-Tuning Convolutional Neural Networks Using Harmony Search
de Rosa, G. H., Papa, J. P., Marana, A. N., Scheirer, W. J., & Cox, D. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25751-8_82 · Cited by 60
Barrett’s Esophagus Analysis Using Convolutional Neural Networks
Mendel, R., Ebigbo, A., Probst, A., Messmann, H., & Palm, C. (2017) · Informatik aktuell · doi:10.1007/978-3-662-54345-0_23 · Cited by 60
A Systematic Study of Neural Discourse Models for Implicit Discourse Relation
Rutherford, A., Demberg, V., & Xue, N. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-1027 · Cited by 60
Suyama, F. M., Delgado, M., da Silva, R. D., & Centeno, T. M. (2019) · NDT & E International · doi:10.1016/j.ndteint.2019.05.002 · Cited by 60
Predicting the propagation of acoustic waves using deep convolutional neural networks
Alguacil, A., Bauerheim, M., Jacob, M. C., & Moreau, S. (2021) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2021.116285 · Cited by 60
Short Term Electric Load Forecasting Based on Data Transformation and Statistical Machine Learning
Andriopoulos, N., Magklaras, A., Birbas, A. N., Papalexopoulos, A. D., Valouxis, C., Daskalaki, S., Birbas, M., Housos, E., & Papaioannou, G. P. (2020) · Applied Sciences · doi:10.3390/app11010158 · Cited by 60
“ReLU has also proven to be an effective solution to resolve vanishing gradient problems when training a CNN using the backpropagation algorithm [55,56].”
BackgroundA Comparative Study of Window Size and Channel Arrangement on EEG-Emotion Recognition Using Deep CNN
Keelawat, P., Thammasan, N., Numao, M., & Kijsirikul, B. (2021) · Sensors · doi:10.3390/s21051678 · Cited by 60
“In particular, CNN benefits from the locality of input and is successful in finding an edge in image classification tasks [37].”
BackgroundMultiple Attention-Guided Capsule Networks for Hyperspectral Image Classification
Paoletti, M. E., Moreno‐Álvarez, S., & Haut, J. M. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3135506 · Cited by 60
“Indeed, the convolutional neural network (CNN) [23], [24] has paved the way for a wide range of deep artificial neural networks (DANNs) for RS-HSI data processing [25], [26].”
BackgroundRecognizing Semantic Features in Faces using Deep LearningPreprint
Gudi, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.00743 · Cited by 60
“stride of 1 both dimensions. The number of parallel feature-maps in this layer is 64. The 44 44 output image produced by this layer is passed to a local contrast normalization and a max-pooling layer [9] of kernel size 3 3 with a stride of 2 in each dimension (selection based on previous work in [12,18]). This results…”
BackgroundMethodFacial Expression Recognition Using Kinect Depth Sensor and Convolutional Neural Networks
Ijjina, E. P., & Mohan, C. K. (2014) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2014.70 · Cited by 59
RAPIDNN: In-Memory Deep Neural Network Acceleration FrameworkPreprint
Imani, M., Samragh, M., Kim, Y., Gupta, S., Koushanfar, F., & Rosing, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.05794 · Cited by 59
“In particular, deep neural networks (DNNs) demonstrate superior effectiveness for diverse classification problems, image processing, video segmentation, speech recognition, computer vision and gaming [2], [3], [4],”
BackgroundRethinking Attention-Model Explainability through Faithfulness Violation TestPreprint
Liu, Y., Li, H., Guo, Y., Kong, C., Li, J., & Wang, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.12114 · Cited by 59
“As shown before in Figure 4 and Figure 5, the explanation methods which perform well on the general attention models (e.g., CNN+DotAtt) often exhibit a worse faithfulness on the transformer-based models, e.g., an increase of 14% violation ratio in AttGrad.”
MethodInfluentialPashaei, A., Ghatee, M., & Sajedi, H. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-019-00852-3 · Cited by 58
“It provides a good description about the image including useful features that can be applied for classification purposes [17, 18].”
BackgroundA deep learning-based framework for lung cancer survival analysis with biomarker interpretation
Cui, L., Li, H., Hui, W., Chen, S., Yang, L., Kang, Y., Bo, Q., & Feng, J. H. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-3431-z · Cited by 59
Evaluation of Salmon, Tuna, and Beef Freshness Using a Portable Spectrometer
Moon, E. J., Kim, Y., Xu, Y., Na, Y., Giaccia, A. J., & Lee, J. (2020) · Sensors · doi:10.3390/s20154299 · Cited by 58
“Samples were scanned with a VIS/NIR portable spectrometer and spectral data was analyzed using the Convolutional Neural Network (CNN)-based machine learning algorithm to evaluate the freshness of the objects [13,14].”
MethodWang, W., Zhang, B., Wu, K., Chepinskiy, S. A., Zhilenkov, A., Chernyi, S., & Krasnov, A. Y. (2021) · Transactions of the Institute of Measurement and Control · doi:10.1177/0142331220987917 · Cited by 59
“The invention of the CNN was inspired by animal’s visual cortex (LeCun et al., 2010), the basic idea of all CNNs can be summed up as local receptive fields, shared biases and weights, pooling techniques.”
MethodAutomated Ensemble Multimodal Machine Learning for Healthcare
Imrie, F., Denner, S., Brunschwig, L. S., Maier-Hein, K. H., & van der Schaar, M. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3530156 · Cited by 57
Cattle Race Classification Using Gray Level Co-occurrence Matrix Convolutional Neural Networks
Santoni, M. M., Sensuse, D. I., Arymurthy, A. M., & Fanany, M. I. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.07.525 · Cited by 57
Assessment of Parkinson’s Disease Based on Deep Neural Networks
Tagaris, A., Kollias, D., & Stafylopatis, A. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-65172-9_33 · Cited by 57
Du, J., Tang, L., Xiang, Y., Zhi, D., Xu, J., Song, H.-Y., & Tao, C. (2018) · Journal of Medical Internet Research · doi:10.2196/jmir.9413 · Cited by 53
“Commonly used in various computer vision tasks [28], convolutional neural networks (CNNs) have demonstrated excellent performance in the NLP field, including different text classification tasks [29-32].”
BackgroundYaddaden, Y., Adda, M., Bouzouane, A., Gaboury, S., & Bouchard, B. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.06.033 · Cited by 57
Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigm
Kollias, D., & Zafeiriou, S. P. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489340 · Cited by 57
Two-Stream Attention Network for Pain Recognition from Video Sequences
Thiam, P., Kestler, H. A., & Schwenker, F. (2020) · Sensors · doi:10.3390/s20030839 · Cited by 57
“Furthermore, Zhou et al. [44] propose a Recurrent Convolutional Neural Network (RCNN) [45] architecture for the continuous estimation of pain intensity in video sequences at the frame-level, whereas Wang et al. [46] propose a transfer learning approach, consisting of the regularisation of a face verification network,…”
BackgroundInfluentialDriver identification using only the CAN-Bus vehicle data through an RCN deep learning approach
Abdennour, N., Ouni, T., & Amor, N. B. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103707 · Cited by 57
Automated early breast cancer detection and classification system
Hekal, A. A., Elnakib, A. A., & Moustafa, H. E.-D. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-01882-w · Cited by 57
“A convolutional neural network (CNN) consists of two types of layers; convolutional layers to extract lower-and higher-order image features, and fully connected layers to perform the classification [24–26].”
BackgroundDetection of rumor conversations in Twitter using graph convolutional networks
Lotfi, S., Mirzarezaee, M., Hosseinzadeh, M., & Seydi, V. (2021) · Applied Intelligence · doi:10.1007/s10489-020-02036-0 · Cited by 56
“The two most widely implemented paradigms in neural networks are RNN and CNN. CNNs have been widely studied for image recognition and processing [21], crowd density estimation [22] and character verification on integrated circuit components of printed circuit boards [23].”
BackgroundLopes, M. K. S., Cassani, R., & Falk, T. H. (2023) · Computational Intelligence and Neuroscience · doi:10.1155/2023/3198066 · Cited by 56
Unclonable Photonic Crystal Hydrogels with Controllable Encoding Capacity for Anticounterfeiting
Wu, J., Li, J., Liu, X., Gong, L., Chen, J., Tang, Z., Lin, W., Mu, Y., Lin, X., Hong, W., et al. (2021) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.1c20905 · Cited by 56
End-to-end Deep Learning from Raw Sensor Data: Atrial Fibrillation Detection using Wearables
Gotlibovych, I., Crawford, S. L., Goyal, D., Liu, J., Kerem, Y., Benaron, D. A., Yilmaz, D., Marcus, G. M., & Li, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.10707 · Cited by 21
“Convolutional layers [30] with ReLU non-linearities [17, 26] extract multiple new features each layer, based on a receptive field of fixed length.”
BackgroundAn Efficient Deep Learning Model to Detect COVID-19 Using Chest X-ray Images
Chakraborty, S., Murali, B., & Mitra, A. K. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19042013 · Cited by 55
“It is widely used in different types of classification problem as well as in image classification problems [48–50].”
Structural color‐based physical unclonable function
Lin, X., Shi, D., Yi, G., & Yu, D. (2024) · Responsive materials · doi:10.1002/rpm.20230031 · Cited by 55
A deep learning approach for Maize Lethal Necrosis and Maize Streak Virus disease detection
O’Halloran, T., Obaido, G., Otegbade, B., & Mienye, I. D. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100556 · Cited by 55
Efficient neural network acceleration on GPGPU using content addressable memory
Imani, M., Peroni, D., Kim, Y., Rahimi, A., & Rosing, T. (2017) · Design, Automation, and Test in Europe · doi:10.23919/date.2017.7927141 · Cited by 55
“In particular, CNNs have been demonstrated to be an effective class of models for image processing, video segmentation, detection and retrieval, speech recognition, computer vision and gaming [4], [5], [6].”
MethodZhang, L., Dolwani, S., & Ye, X. (2017) · Communications in computer and information science · doi:10.1007/978-3-319-60964-5_62 · Cited by 55
Peak alignment of gas chromatography–mass spectrometry data with deep learning
Li, M., & Wang, X. R. (2019) · Journal of Chromatography A · doi:10.1016/j.chroma.2019.460476 · Cited by 55
“Since around 2012, it has become one of the most popular machine learning methods for many types of complex problems such as image classification [34, 35, 36], speech recognition [37, 38], language translation [39], handwriting transcription [40, 41], autonomous driving [42], to name a few.”
BackgroundDeep learning based HEp-2 image classification: A comprehensive review
Rahman, S., Wang, L., Sun, C., & Zhou, L. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101764 · Cited by 55
Research and Discussion on Image Recognition and Classification Algorithm Based on Deep Learning
Dong, Y.-N., & Liang, G.-S. (2019) · International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI) · doi:10.1109/mlbdbi48998.2019.00061 · Cited by 55
Rani, N., Das, P., & Bhardwaj, A. K. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6479 · Cited by 56
Zhang, T., Aftab, W., Mihaylova, L., Langran-Wheeler, C., Rigby, S. E., Fletcher, D. I., Maddock, S., & Bosworth, G. (2022) · Sensors · doi:10.3390/s22124324 · Cited by 55
“In recent years, various deep learning models developed based on CNNs have been demonstrated with strong robustness performance on image datasets such as ImageNet [49], which makes it the most popular deep learning framework in the area of computer vision [52].”
BackgroundAnalysis of time-frequency scattering transforms
Czaja, W., & Li, W. (2017) · Applied and Computational Harmonic Analysis · doi:10.1016/j.acha.2017.08.005 · Cited by 55
“ions. Each transformation is either predetermined or trained through a learning process, and consists of three operators: a convolution against a lter bank, a non-linearity, and an averaging operator [LKF10]. Neural networks are typically used as feature extractors, and when combined with standard classiers, they have…”
MethodDeep Learning for Classification of Dental Plaque Images
Imangaliyev, S., van der Veen, M. H., Volgenant, C. M. C., Keijser, B. J. F., Crielaard, W., & Levin, E. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-51469-7_34 · Cited by 54
Visual Sentiment Analysis for Review Images with Item-Oriented and User-Oriented CNN
Truong, Q.-T., & Lauw, H. W. (2017) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3123266.3123374 · Cited by 54
“CNN has been successfully used in learning tasks such as handwriting recognition [18], document recognition [19], feature learning [20], sentence classication [15], image classication [17].”
MethodTran, P., Thoprakarn, U., Gourieux, E., dos Santos, C. L., Cavedo, E., Guizard, N., Cotton, F., Krolak‐Salmon, P., Delmaire, C., Heidelberg, D., et al. (2022) · NeuroImage Clinical · doi:10.1016/j.nicl.2022.102940 · Cited by 54
Lim, H., Kornijčuk, V., Seok, J. Y., Kim, S. K., Kim, I., Hwang, C. S., & Jeong, D. S. (2015) · Scientific Reports · doi:10.1038/srep09776 · Cited by 54
Kainz, P., Pfeiffer, M., & Urschler, M. (2015) · arXiv (Cornell University) · doi:10.5167/uzh-121723 · Cited by 55
Chen, C., Wu, Z., Lai, Y., Ou, W., Liao, T., & Zheng, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.00419 · Cited by 54
“Convolutional neural networks (CNN) [114, 211] have long been the standard backbone in computer vision, the core of which lies in the design of its convolutional layers, which not only share parameter weights but also are able to extract features.”
BackgroundAn Overview of FPGA Based Deep Learning Accelerators: Challenges and Opportunities
Wang, T., Wang, C., Zhou, X., & Chen, H. (2019) · 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc/smartcity/dss.2019.00229 · Cited by 53
“is the first right multi-layer structure learning algorithm [5], which uses relative spatial relations to reduce the number of parameters to improve training performance.”
BackgroundRobust Downbeat Tracking Using an Ensemble of Convolutional Networks
Durand, S., Bello, J. P., David, B., & Richard, G. (2016) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2016.2623565 · Cited by 55
“In CNNs, convolutional layers [37], [38] share weights across the inputs within a spatiotemporal region so each input unit is not considered independent from its neighbors.”
BackgroundLei, J. W., Li, G., Zhang, J., Guo, Q., & Tu, D. (2016) · IET Computer Vision · doi:10.1049/iet-cvi.2015.0408 · Cited by 53
“Convolutional neural network (CNN) [6, 7], one type of deep models, has been demonstrated as an effective model to learn high-level features directly from raw data.”
BackgroundLip reading using a dynamic feature of lip images and convolutional neural networks
Li, Y., Takashima, Y., Takiguchi, T., & Ariki, Y. (2016) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis.2016.7550888 · Cited by 53
Convolutional Neural Networks Based on RRAM Devices for Image Recognition and Online Learning Tasks
Dong, Z., Zhou, Z., Li, Z., Liu, C., Huang, P., Liu, L., Liu, X., & Kang, J. (2019) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2018.2882779 · Cited by 47
Multiclass Breast Cancer Classification Using Convolutional Neural Network
Nguyen, P. T., Nguyen, T. T., Nguyen, N. C., & Le, T. T. (2019) · IEEE International Symposium on Electronics and the Environment (ISEE) · doi:10.1109/isee2.2019.8920916 · Cited by 53
“In a nutshell, CNN consists of several stages stacked, followed by supervised classifications and forming feature maps representing both the input and output of each stage in the structure of CNN [12].”
MethodExtracting human attributes using a convolutional neural network approach
Perlin, H. A., & Lopes, H. S. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.07.012 · Cited by 52
Land-use scene classification based on a CNN using a constrained extreme learning machine
Weng, Q., Mao, Z., Lin, J., & Liao, X. (2018) · International Journal of Remote Sensing · doi:10.1080/01431161.2018.1458346 · Cited by 53
“Convolutional neural network (CNN) is one of the deep learning methods, which consists of a number of convolutional and pooling layers and a fully connected layer (FCL) as the classi fi er (Dahl et al. 2010).”
Background
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.