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 301–400 of 1,001
A deep semantic mobile application for thyroid cytopathology
Kim, E., Corte-Real, M., & Baloch, Z. (2016) · SPIE Proceedings · doi:10.1117/12.2216468 · Cited by 90
A Study of Garbage Classification with Convolutional Neural Networks
Meng, S., & Chu, W.-T. (2020) · Indo-Taiwan International Conference on Computing, Analytics and Networks (Indo-Taiwan ICAN) · doi:10.1109/indo-taiwanican48429.2020.9181311 · Cited by 99
“Among various deep models, convolutional neural networks(CNNs) [2, 3] especially have led to a series of breakthroughs for image classification.”
BackgroundTraffic Sign Recognition Using Deep Convolutional Networks and Extreme Learning Machine
Zeng, Y., Xu, X., Fang, Y., & Zhao, K. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23989-7_28 · Cited by 99
Mutual exclusivity loss for semi-supervised deep learning
Sajjadi, M., Javanmardi, M., & Tasdizen, T. (2016) · 2016 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2016.7532690 · Cited by 75
“Unlabeled data has also been used for pre-training of convolutional layers in a ConvNet [9, 10] in an effort to reduce the amount of labeled data required during supervised training.”
MethodIntracerebral EEG Artifact Identification Using Convolutional Neural Networks
Nejedlý, P., Cimbálník, J., Klimeš, P., Plešinger, F., Halámek, J., Křemen, V., Viščor, I., Brinkmann, B. H., Pail, M., Brázdil, M., et al. (2018) · Neuroinformatics · doi:10.1007/s12021-018-9397-6 · Cited by 99
“More sophisticated descriptions can be found in (LeCun 1988, 2015; LeCun and Kavukcuoglu 2010; Lecun and Bengio 1995).”
BackgroundSaxena, S., & Gyanchandani, M. (2020) · Journal of Medical Imaging and Radiation Sciences · doi:10.1016/j.jmir.2019.11.001 · Cited by 89
Principles of Temporal Processing Across the Cortical Hierarchy
Himberger, K. D., Chien, H.-Y., & Honey, C. J. (2018) · Neuroscience · doi:10.1016/j.neuroscience.2018.04.030 · Cited by 88
Chauhan, R., Kaur, H., & Alankar, B. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2021.103239 · Cited by 96
Feature Extraction with Convolutional Neural Networks for Handwritten Word Recognition
Bluche, T., Ney, H., & Kermorvant, C. (2013) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2013.64 · Cited by 95
“They have been successfully applied to computer vision problems, particularly to isolated character recognition [8], [9], [7] and handwriting recognition [10], [11].”
BackgroundJoint Time–Frequency Scattering
Andén, J., Lostanlen, V., & Mallat, S. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2918992 · Cited by 95
“A convolutional network cascades convolutions, subsampling operators, and pointwise nonlinearities (such as rectifiers) [10],”
BackgroundSemi-Supervised Sequence Modeling with Cross-View TrainingPreprint
Clark, K., Luong, M.-T., Manning, C. D., & Le, Q. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.08370 · Cited by 96
“Early approaches to deep semi-supervised learning pre-train neural models on unlabeled data, which has been successful for applications in computer vision (Jarrett et al., 2009; LeCun et al., 2010) and NLP.”
BackgroundGobert, C., Kudzal, A., Sietins, J. M., Mock, C., Sun, J., & McWilliams, B. (2020) · Additive manufacturing · doi:10.1016/j.addma.2020.101460 · Cited by 94
Time Series Prediction of Wastewater Flow Rate by Bidirectional LSTM Deep Learning
Kang, H., Yang, S., Huang, J., & Oh, J. (2020) · International Journal of Control Automation and Systems · doi:10.1007/s12555-019-0984-6 · Cited by 93
“Deep learning, as both unsupervised deep belief nets [1,2] and supervised convolutional neural nets [3,4], has been widely used in many real-world applications such as speech recognition, image classification, vision, and regression or prediction of time series.”
BackgroundMüller, D., Muller, M. G., Kreß, D., & Pesch, E. (2022) · European Journal of Operational Research · doi:10.1016/j.ejor.2022.01.034 · Cited by 93
Wen, S., Chen, J., Wu, Y., Yan, Z., Cao, Y., Yang, Y., & Huang, T. (2020) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2020.3019993 · Cited by 92
Classification of Gait Type Based on Deep Learning Using Various Sensors with Smart Insole
Lee, S.-S., Choi, S. T., & Choi, S. (2019) · Sensors · doi:10.3390/s19081757 · Cited by 92
“We constructed a deep neural network for data classification based on deep convolutional neural network (DCNN) [22].”
BackgroundMethodYu, R., Liu, Z., Li, X., Lu, W., Ma, D., Yu, M., Wang, J., & Li, B. (2019) · Applied Energy · doi:10.1016/j.apenergy.2019.01.010 · Cited by 91
Deep Learning 3D Sparse Inversion of Gravity Data
Huang, R., Liu, S., Qi, R., & Zhang, Y. (2021) · Journal of Geophysical Research Solid Earth · doi:10.1029/2021jb022476 · Cited by 92
“Current studies provide new perspectives for the reconstruction of density models from gravity data, among which convolutional neural networks (CNNs) are an important technique, achieving nonlinear activation after linear combination (LeCun et al., 2010).”
BackgroundA General Machine Learning Model for Assessing Fruit Quality Using Deep Image Features
Apostolopoulos, I. D., Tzani, M., & Aznaouridis, S. I. (2023) · AI · doi:10.3390/ai4040041 · Cited by 91
“ViT allows for effective self-attention mechanisms in image classification tasks, providing a promising alternative to traditional convolutional neural networks (CNNs) [18].”
BackgroundRavi Raj, K. G., & Kos, A. (2025) · Sensors · doi:10.3390/s25041033 · Cited by 91
Learning Optical Flow with Kernel Patch Attention
Luo, A., Yang, F., Li, X. S., & Liu, S. (2022) · 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/cvpr52688.2022.00870 · Cited by 90
“Specifically, inspired by image and point convolutions [23,37], we formulate KPA as a kernel-based operator, which is generally given by:”
BackgroundMethodUse of Artificial Intelligence in the Classification of Elementary Oral Lesions from Clinical Images
Gomes, R. F. T., Schmith, J., de Figueiredo, R. M., Freitas, S. A., Machado, G. N., Romanini, J., & Carrard, V. C. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20053894 · Cited by 90
“By assembling these sub-images, the image is process d and interpreted [10].”
BackgroundInfluentialDriver yawning detection based on deep convolutional neural learning and robust nose tracking
Zhang, W., Murphey, Y. L., Wang, T., & Xu, Q. (2015) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2015.7280566 · Cited by 90
Multi-Stream Convolutional Neural Network for SAR Automatic Target Recognition
Zhao, P., Liu, K., Zou, H., & Zhen, X. (2018) · Remote Sensing · doi:10.3390/rs10091473 · Cited by 89
“In this paper, the max pooling operator is utilized [21], and the relevant operation only reserves the maximum value within the pooling-size region extracted from a certain filter, so this operation is processed in each feature map separately.”
MethodBreast cancer classification using deep learned features boosted with handcrafted features
Sajid, U., Khan, R. A., Shah, S. M., & Arif, S. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105353 · Cited by 89
“The architecture of CNN was initially proposed by LeCun [57].”
MethodEnd-to-End Neural Network Based Automated Speech Scoring
Chen, L., Tao, J., Ghaffarzadegan, S., & Qian, Y. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8462562 · Cited by 89
“This vector runs through a second dropout layer with probability (dpCNN2).”
MethodInfluentialKhalifa, Y., Mandic, D. P., & Sejdić, E. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.11.008 · Cited by 88
“A pooling layer represents a dimensionality reduction procedure that processes the feature maps in order to produce lower resolution maps that are robust to the small variations in the location of features [206].”
BackgroundMethodInfluentialTan, X., Li, K., Zhang, J., Wang, W., Wu, B., Wu, J., Li, X., & Huang, X. (2021) · Cancer Cell International · doi:10.1186/s12935-020-01742-6 · Cited by 87
“Convolutional neural networks have the advantages of automatically learning features during training, and possessing strong inferential capabilities in comparison with conventional image processing methods in complex scenes [35, 36].”
BackgroundDeep Residual Network in Network
Alaeddine, H., & Malek, J. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/6659083 · Cited by 89
“…22], increasing the width [19, 23], number of units of each layer and/or the number of feature maps (channels) [23, 24], modification of convolution parameters [25–29] or pooling [30–38], changing the activation function [1, 39, 40], and reducing the number of parameters and resources [1, 27, 41].”
BackgroundDeep neural networks approach to skin lesions classification — A comparative analysis
Kwasigroch, A., Mikołajczyk, A., & Grochowski, M. (2017) · International Conference on Methods and Models in Automation and Robotics · doi:10.1109/mmar.2017.8046978 · Cited by 88
“Basic deep convolutional network architecture [12]”
Facial Expression Recognition Using Visual Saliency and Deep Learning
Mavani, V., Raman, S., & Miyapuram, K. P. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.327 · Cited by 87
Cooke, C., & Scott, K. A. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2892723 · Cited by 88
“In a typical sequential CNN (where there is a single pathway for information), multiscale information is passed sequentially through layers of convolutional filters, rectified linear activations, and downsampling operations [6], [29], [30].”
BackgroundZhang, R., Liu, Q., & Hang, R. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2938204 · Cited by 86
“directly in a hierarchical manner, which significantly improves the performance of image processing tasks such as object detection, classification, and semantic segmentation [21]–[25].”
BackgroundZheng, C., Chen, C., Chen, Y., & Ong, S. P. (2020) · Patterns · doi:10.1016/j.patter.2020.100013 · Cited by 86
Yadav, Y., & Chand, S. (2020) · Machine Vision and Applications · doi:10.1007/s00138-020-01094-1 · Cited by 86
“The deep learning methods based on convolution neural networks (CNN) [10] use the high level and robust features for different tasks such as in biomedical image analysis tasks like mitosis detection [11], semantic segmentation [12], classification [13], and blood cell counting [14] .”
MethodInfluentialA new ensemble learning approach to detect malaria from microscopic red blood cell images
Bhuiyan, M., & Islam, M. S. (2022) · Sensors International · doi:10.1016/j.sintl.2022.100209 · Cited by 86
Computer vision meets microfluidics: a label-free method for high-throughput cell analysis
Zhou, S., Chen, B., Fu, E. S., & Yan, H. G. (2023) · Microsystems & Nanoengineering · doi:10.1038/s41378-023-00562-8 · Cited by 88
“To make neural networks more suitable for image analysis, researchers proposed convolutional neural networks (CNNs) 13,14 , and the architecture of CNNs was inspired by the visual data processing mechanism underlying the human visual cortex.”
MethodWiebe, N., Kapoor, A., & Svore, K. M. (2016) · Quantum Information and Computation · doi:10.26421/qic16.7-8-1 · Cited by 85
“Deep learning is a recent technique for machine learning that has substantially impacted the way in which classification, inference, and artificial intelligence (AI) tasks are modeled [1–4].”
BackgroundA new method for automatic seismic fault detection using convolutional neural network
Guo, B., Li, L., & Luo, Y. (2018) · Second International Meeting for Applied Geoscience & Energy · doi:10.1190/segam2018-2995894.1 · Cited by 85
Cross-View Gait Recognition with Deep Universal Linear Embeddings
Zhang, S., Wang, Y., & Li, A. (2021) · 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/cvpr46437.2021.00898 · Cited by 84
“Similar ConvNets can be found in [32, 48, 49].”
InfluentialAutomatic Neuron Detection in Calcium Imaging Data Using Convolutional NetworksPreprint
Apthorpe, N., Riordan, A. J., Aguilar, R., Homann, J., Gu, Y., Tank, D. W., & Seung, H. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.07372 · Cited by 84
“Supervised learning has become the dominant approach for attaining high accuracy in many computer vision problems [12].”
BackgroundKnee Osteoarthritis Classification Using 3D CNN and MRI
Guida, C., Zhang, M., & Shan, J. (2021) · Applied Sciences · doi:10.3390/app11115196 · Cited by 83
“Convolutional neural networks (CNNs) are a class of deep learning techniques that are designed to work with images and can remove the need for handcrafted feature extractors [14].”
BackgroundWind power prediction based on a convolutional neural network
Zhu, A., Li, X., Mo, Z., & Wu, R. (2017) · International Conference on Circuits, Devices and Systems (ICCDS) · doi:10.1109/iccds.2017.8120465 · Cited by 83
“As a multi-layer perceptron, which is specially designed for the recognition of two-dimensional shapes, CNN has a high degree of invariance for translation, scaling, inclination, or deformation in other forms [6].”
BackgroundA novel database of children's spontaneous facial expressions (LIRIS-CSE)
Khan, R. A., Crenn, A., Meyer, A., & Bouakaz, S. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.02.004 · Cited by 82
“In current era where requirement of amount of data for learning a concept / computational model (deep learning [15]) has increased exponentially, only few hundred static images are not enough.”
Deep Fisher Kernels -- End to End Learning of the Fisher Kernel GMM Parameters
Sydorov, V., Sakurada, M., & Lampert, C. H. (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.2014.182 · Cited by 83
“, these overviews on object categorization [32], image kernels [19], and deep representation learning [4, 23].”
BackgroundDeep learning algorithm for breast masses classification in mammograms
Gnanasekaran, V. S., Joypaul, S., Sundaram, P. M., & Chairman, D. D. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2020.0070 · Cited by 82
“Each filter bank detects a particular feature at each location on the input map [24].”
BackgroundFu, T., Ma, L., Li, M., & Johnson, B. A. (2018) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.12.025010 · Cited by 82
“convolution phase, trainable filterW (convolution kernel) performs the convolution operation by using a sliding window technique.(62,63) Assume the convolution kernel is i × j in size, and then, the output feature map Y that corresponds to X can be written as follows:”
Methodde Oliveira, D. C., & Wehrmeister, M. A. (2018) · Sensors · doi:10.3390/s18072244 · Cited by 87
“Since the CNN needs a large-scale set of data for the training step [47], we conducted a data augmentation process to increase the number of samples in the dataset.”
MethodChoi, H., Park, M., Son, G., Jeong, J.-Y., Park, J.-S., Mo, K., & Kang, P. (2020) · Ocean Engineering · doi:10.1016/j.oceaneng.2020.107129 · Cited by 81
Tandem HMM with convolutional neural network for handwritten word recognition
Bluche, T., Ney, H., & Kermorvant, C. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6638083 · Cited by 81
Emotion recognition by assisted learning with convolutional neural networks
He, X., & Zhang, W. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.02.073 · Cited by 81
Reddy, D. S., Bharath, R., & Rajalakshmi, P. (2018) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom.2018.8531118 · Cited by 81
“Particularly, CNN’s have been proven to be an efficient and reliable method for many of the computer vision tasks [8]–[10], which automatically learns mid-level and highlevel abstractions from the database [11].”
MethodRes-DNN: A Residue Number System-Based DNN Accelerator Unit
Samimi, N., Kamal, M., Afzali‐Kusha, A., & Pedram, M. (2019) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2019.2951083 · Cited by 80
“THE high accuracy of DNNs makes them appropriate for use in many applications such as speech recognition [1], face detection [2], autonomous vehicles [3], and scene understanding [4].”
BackgroundDrug-Target Interaction Prediction: End-to-End Deep Learning Approach
Monteiro, N. R. C., Ribeiro, B., & Arrais, J. P. (2020) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2020.2977335 · Cited by 80
Li, J., Un, K.-F., Yu, W.-H., Mak, P., & Martins, R. P. (2021) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2021.3095283 · Cited by 80
Boston, T., van Dijk, A. I. J. M., Larraondo, P., & Thackway, R. (2022) · Remote Sensing · doi:10.3390/rs14143396 · Cited by 80
Interest Point Detector and Feature Descriptor Survey
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_6 · Cited by 83
Intermittent process analysis with scattering moments
Bruna, J., Mallat, S., Bacry, E., & Muzy, J. (2015) · The Annals of Statistics · doi:10.1214/14-aos1276 · Cited by 80
“These algorithms are implemented with deep convolutional neural network structures [24].”
MethodSAR Image Classification via Deep Recurrent Encoding Neural Networks
Geng, J., Wang, H., Fan, J., & Ma, X. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2777868 · Cited by 80
“Typical deep models include deep belief networks [24], convolutional NNs (CNNs) [25], stacked autoencoders (SAEs) [26], [27], and recurrent NNs (RNNs) [28].”
BackgroundDeep belief networks and cortical algorithms: A comparative study for supervised classification
Rizk, Y., Hajj, N., Mitri, N., & Awad, M. (2018) · Applied Computing and Informatics · doi:10.1016/j.aci.2018.01.004 · Cited by 80
Semantic segmentation of PolSAR image data using advanced deep learning model
Garg, R., Kumar, A., Bansal, N., Prateek, M., & Kumar, S. (2021) · Scientific Reports · doi:10.1038/s41598-021-94422-y · Cited by 80
“The Deep Neural Network (DNN) models include deep Boltzmann machines 30 , Convolutional Neural Networks 31,32 , Deep Belief Networks (DBNs) 33 , and Stacked Auto Encoders (SAEs) 34 .”
MethodUnderstanding Convolutional Neural Networks
Stutz, D. (2014) · Cited by 79
Qu, T., Zhang, Q., & Sun, S. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-4043-5 · Cited by 80
“In this study, the database used is the DLR Munich Vehicle dataset offered by the Remote Sensing Technology Institute of the German Aerospace Centre [14, 16].”
Rubo, R. A., Carneiro, C. D. C., Michelon, M. F., & Gioria, R. D. S. (2019) · Journal of Petroleum Science and Engineering · doi:10.1016/j.petrol.2019.106382 · Cited by 79
CVSnet: A machine learning approach for automated central vein sign assessment in multiple sclerosis
Maggi, P., Fartaria, M. J., Jorge, J., Rosa, F. L., Absinta, M., Sati, P., Meuli, R. A., Pasquier, R. D., Reich, D. S., Cuadra, M. B., et al. (2020) · NMR in Biomedicine · doi:10.1002/nbm.4283 · Cited by 81
“CVSnet, our approach to automatically assess the CVS, is based on a 3D convolutional neural network architecture.(21,22) Because it uses deep learning, it is an end-to-end learning approach that does not require handcrafted discriminative features or filters.”
MethodSalb, M., Jovanović, L., Bačanin, N., Antonijević, M., Zivkovic, M. Z., Budimirović, N., & Abualigah, L. (2023) · Applied Sciences · doi:10.3390/app132312687 · Cited by 79
“Yann LeCun’s paper highlights the effectiveness of gradient-based learning techniques in training these filters [22].”
BackgroundZou, Y., Li, L., Wang, Y., Yu, J., Li, Y., & Deng, W. (2015) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/icdsp.2015.7252086 · Cited by 79
“Hence spatially translating the input of a feature detection layer will translate the output but leave it otherwise unchanged [12].”
Background3D gesture classification with convolutional neural networks
Duffner, S., Berlemont, S., Lefebvre, G., & Garcia, C. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6854641 · Cited by 65
“Classical ConvNets [12, 13] have been used successfully for computer vision tasks, where the input is a 2D image or image sequence and the convolution filters extract simple 2D features (like edges) in the first layer(s) and more complex features (like corners) in the subsequents layer(s).”
MethodInfluentialDetecting predatory conversations in social media by deep convolutional neural networks
Ebrahimi, M., Suen, C. Y., & Ormandjieva, O. (2016) · Digital Investigation · doi:10.1016/j.diin.2016.07.001 · Cited by 78
“Being inspired by biological visual system, CNNs have been successfully used in various image processing tasks (LeCun et al., 2010).”
MethodForecast of Solar Energy Production - A Deep Learning Approach
Zhang, R., Feng, M., Zhang, W., Lu, S., & Wang, F. (2018) · IEEE International Conference on Big Knowledge (ICBK) · doi:10.1109/icbk.2018.00018 · Cited by 78
“, object recognition in computer vision [17], [18], image classification [19], [20], [21], image captioning [22], [23], Go game in competition with best human players [24], speech recognition [25], [26], natural language processing [27], [28], etc.”
BackgroundAutomatic Modulation Classification Scheme Based on LSTM With Random Erasing and Attention Mechanism
Chen, Y., Shao, W., Liu, J., Yu, L., & Qian, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3017641 · Cited by 78
“Among them, CNN [21] and ResNet [22] can improve the affect of signal frequency offset on classification accuracy; LSTM is suitable for feature extraction of time series signals [19]; while Convolutional, LSTM, Deep Neural Network (CLDNN) combines the advantages of DNN, CNN and LSTM, and is proved…”
BackgroundBahathiq, R. A., Banjar, H. R., Bamaga, A. K., & Jarraya, S. K. (2022) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2022.949926 · Cited by 78
“This layer classifies the image into different categories (LeCun et al., 2010; Ozonoff et al., 2011).”
BackgroundInfluentialPlayer Tracking Data in Sports
Kovalchik, S. A. (2022) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-033021-110117 · Cited by 78
Cloth Funnels: Canonicalized-Alignment for Multi-Purpose Garment Manipulation
Canberk, A., Chi, C., Ha, H., Burchfiel, B., Cousineau, E. A., Feng, S., & Song, S. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161546 · Cited by 79
“Spatial Action Maps is a convolutional neural network [29] (CNN) policy for learning value maps [30] where actions are defined on a pixel grid.”
BackgroundVijh, S., Sharma, S. B., & Gaurav, P. (2019) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-25797-2_8 · Cited by 78
Nogueira, R. F., & Lotufo, R. (2014) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 78
Natale, L. D., Svetozarevic, B., Heer, P., & Jones, C. N. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.121071 · Cited by 78
CGBVS‐DNN: Prediction of Compound‐protein Interactions Based on Deep Learning
Hamanaka, M., Taneishi, K., Iwata, H., Ye, J., Pei, J., Hou, J., & Okuno, Y. (2017) · Molecular Informatics · doi:10.1002/minf.201600045 · Cited by 70
Deep learning based monitoring of furnace combustion state and measurement of heat release rate
Wang, Z., Song, C., & Chen, T. (2017) · Energy · doi:10.1016/j.energy.2017.05.012 · Cited by 77
Li, T., Zhao, Z., Sun, C., Yan, R., & Chen, X. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.2980596 · Cited by 77
“CNNs mainly consist of the convolutional layer, the pooling layer and the fully connected layer [41].”
BackgroundWang, Z., & Oates, T. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.07481 · Cited by 77
“CNNs are the state-of-the-art approach in various image recognition and computer vision tasks [10, 11, 12].”
BackgroundFast Deep Convolutional Face Detection in the Wild Exploiting Hard Sample Mining
Triantafyllidou, D., Nousi, P., & Tefas, A. (2017) · Big Data Research · doi:10.1016/j.bdr.2017.06.002 · Cited by 76
Liu, W., Li, C., Rahaman, M. M., Jiang, T., Sun, H., Wu, X., Hu, W., Chen, H., Sun, C., Yao, Y., et al. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105026 · Cited by 75
“A CNN model clas-sifies normal and abnormal cells in the cell clas-sification task by extracting hierarchical features from the original image [19].”
MethodA Hierarchical Predictive Coding Model of Object Recognition in Natural Images
Spratling, M. W. (2017) · Cognitive Computation · doi:10.1007/s12559-016-9445-1 · Cited by 66
Liu, C., Hu, S.-C., Wang, C., Lafata, K. J., & Yin, F.-F. (2020) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-19-883 · Cited by 74
“Convolutional neural networks (CNN) is the most common deep learning technique in imaging science, with the ability to perform pixelwise feature extraction (8).”
BackgroundTran, T. S., Tran, V. P., Lee, H. J., Flores, J. M., & Le, V. P. (2020) · International Journal of Pavement Engineering · doi:10.1080/10298436.2020.1836561 · Cited by 74
“One of the most common deep learning technique used is the convolutional neural network (CNN), which is inspired by the structure of the visual system for image classification (LeCun et al. 2010).”
MethodDifferential diagnosis of benign and malignant vertebral fracture on CT using deep learning
Li, Y., Zhang, Y., Zhang, E., Chen, Y., Wang, Q., Liu, K., Yu, H. J., Yuan, H., Lang, N., & Su, M. (2021) · European Radiology · doi:10.1007/s00330-021-08014-5 · Cited by 74
“Deep learning shows strong processing ability and information retention ability [30, 31], superior to machine learning or radiomics that rely on parameters extracted using pre-defined methods [32].”
MethodA multichannel optical computing architecture for advanced machine vision
Xu, Z., Yuan, X., Zhou, T., & Fang, L. (2022) · Light Science & Applications · doi:10.1038/s41377-022-00945-y · Cited by 74
Chinese Herbal Medicine Image Recognition and Retrieval by Convolutional Neural Network
Sun, X., & Qian, H. (2016) · PLoS ONE · doi:10.1371/journal.pone.0156327 · Cited by 73
“In recent years, with the development of parallel computing, the Convolutional Neural Network (CNN) that was proposed several decades ago has re-dominated the area of image recognition [26 – 31 , 33 –”
BackgroundDiffusion Scattering Transforms on GraphsPreprint
Gama, F., Ribeiro, A., & Bruna, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.08829 · Cited by 73
“Each of the layers in a CNN is itself the composition of a convolution operation with a pointwise nonlinearity where the filters used at different layers are the outcome of a data-driven optimization process (LeCun et al., 2010; 2015).”
Neutrino interaction classification with a convolutional neural network in the DUNE far detector
Abi, B., Acciarri, R., Acero, M. A., Adamov, G., Adams, D. L., Adinolfi, M., Ahmad, Z., Ahmed, J., Alion, T., Monsalve, S. A., et al. (2020) · Physical review. D/Physical review. D. · doi:10.1103/physrevd.102.092003 · Cited by 72
Çatak, F. Ö., Kuzlu, M., Çatak, E., Cali, Ü., & Güler, Ö. (2022) · IEEE Access · doi:10.1109/access.2022.3206385 · Cited by 73
“The convolutional neural network (CNN) is a neural network that has shown to be very successful for image recognition [27]–[29].”
BackgroundSpratling, M. W. (2012) · Neural Computation · doi:10.1162/neco_a_00222 · Cited by 67
“…belief networks (Hinton et al., 2006) and since the encoder-decoder architecture has been employed in recent versions of convolutional neural networks (Jarrett et al., 2009; LeCun et al., 2010), the full hierarchical PC/BC model can be related to these deep learning methods (Arel et al., 2010).”
MethodOptimization of convolutional neural network using microcanonical annealing algorithm
Ayumi, V., Rere, L. M. R., Fanany, M. I., & Arymurthy, A. M. (2016) · International Conference on Advanced Computer Science and Information Systems · doi:10.1109/icacsis.2016.7872787 · Cited by 73
New Logic-In-Memory Paradigms: An Architectural and Technological Perspective
Santoro, G., Turvani, G., & Graziano, M. (2019) · Micromachines · doi:10.3390/mi10060368 · Cited by 72
Illumination invariant face recognition using convolutional neural networks
Ramaiah, N. P., Ijjina, E. P., & Mohan, C. K. (2015) · IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES) · doi:10.1109/spices.2015.7091490 · Cited by 71
“Over the last decade, convolutional neural networks [11] is widely used for various computer vision tasks [12].”
MethodConvolutional Neural Networks for Long Time Dissipative Quantum Dynamics
Rodríguez, L. E. H., & Kananenka, A. A. (2021) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.1c00079 · Cited by 71
“On the other hand LSTMs are more difficult to train than CNNs [59].”
BackgroundLeung, C. K.-S. (2014) · IGI Global eBooks · doi:10.4018/978-1-4666-5202-6.ch030 · Cited by 71
Detection of Helminthosporium Leaf Blotch Disease Based on UAV Imagery
Huang, H., Deng, J., Lan, Y., Yang, A., Zhang, L., Wen, S., Zhang, H., Zhang, Y., & Deng, Y. (2019) · Applied Sciences · doi:10.3390/app9030558 · Cited by 70
“The input and output of each stage are sets of arrays called feature maps [22].”
BackgroundIn the Pursuit of Effective Affective Computing: The Relationship Between Features and Registration
Chew, S. W., Lucey, P., Lucey, S., Saragih, J., Cohn, J. F., Matthews, I., & Sridharan, S. (2012) · IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2012.2194485 · Cited by 65
“[26] refers to this blurring process more generically as “pooling”, pooling operations other than blurring (e.”
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.