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 501–600 of 1,001
Maize Tassel Detection From UAV Imagery Using Deep Learning
Alzadjali, A., Alali, M. H., Sivakumar, A. N. V., Deogun, J. S., Scott, S., Schnable, J. C., & Shi, Y. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.600410 · Cited by 52
“In a CNN, the convolution is performed on the input data with the use of a filter to then produce a feature map (LeCun et al., 2010).”
MethodGround Truth Data, Content, Metrics, and Analysis
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_7 · Cited by 53
Ball Localization for Robocup Soccer Using Convolutional Neural Networks
Speck, D., Barros, P. V. A., Weber, C., & Wermter, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68792-6_2 · Cited by 51
“have already shown that deep networks are able to learn visual features for comparable tasks in robotics [15].”
BackgroundAutomatic Classification and Accuracy by Deep Learning Using CNN Methods in Lung Chest X-Ray Images
Thamilarasi, V., & Roselin, R. (2021) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1055/1/012099 · Cited by 51
Wear Mechanism Classification Using Artificial Intelligence
Sieberg, P. M., Kurtulan, D., & Hanke, S. (2022) · Materials · doi:10.3390/ma15072358 · Cited by 51
“Basically, there are different types of artificial neural networks, such as recurrent neural networks [20] and convolutional neural networks [21].”
Quantum Denoising Diffusion Models
Kölle, M., Stenzel, G., Stein, J., Zielinski, S., Ommer, B., & Linnhoff–Popien, C. (2024) · IEEE International Conference on Quantum Software (QSW) · doi:10.1109/qsw62656.2024.00023 · Cited by 51
“DCNs are hierarchical models that utilize convolutional layers to extract progressively complex spatial features from input data [12, 23, 25].”
BackgroundMonowar, M. M., Nobel, S. M. N., Afroj, M., Hamid, A., Uddin, M. Z., Kabir, M. M., & Mridha, M. F. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1506770 · Cited by 51
Early Hierarchical Contexts Learned by Convolutional Networks for Image Segmentation
Wu, Z., Huang, Y., Yu, Y., Wang, L., & Tan, T. N. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.273 · Cited by 51
“[17] applied CNN to object recognition and robot navigating.”
MethodStock market direction prediction using deep neural networks
Gündüz, H., Çataltepe, Z., & Yaslan, Y. (2017) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2017.7960512 · Cited by 51
“Kanal kullanımı giriş verisine farklı açılardan bakılmasını sağlar [20].”
Review of Deep Learning Methods in Mammography, Cardiovascular, and Microscopy Image Analysis
Carneiro, G., Zheng, Y., Xing, F., & Yang, L. (2017) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-42999-1_2 · Cited by 52
“Given images and corresponding annotations (or labels), a CNN model is learned to generate hierarchical data representations, which can be used for robust target classification [84].”
MethodColor encoding in biologically-inspired convolutional neural networks
Rafegas, I., & Vanrell, M. (2018) · Vision Research · doi:10.1016/j.visres.2018.03.010 · Cited by 51
Selective peripheral nerve recordings from nerve cuff electrodes using convolutional neural networks
Koh, R. G. L., Balas, M., Nachman, A., & Zariffa, J. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab4ac4 · Cited by 51
“The classification accuracies and ankle angle reconstruction from the firing rates achieved, further support the idea of nCAP-based classification introduced in [32], and demonstrate the benefits of a CNN architecture that can make more effective use of the spatiotemporal information.”
InfluentialAn Ensemble Algorithm Based on Deep Learning for Tuberculosis Classification
Hernández, A., Panizo-LLedot, Á., & Camacho, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33607-3_17 · Cited by 51
Deep recurrent–convolutional neural network for classification of simultaneous EEG–fNIRS signals
Ghonchi, H., Fateh, M., Abolghasemi, V., Ferdowsi, S., & Rezvani, M. (2020) · IET Signal Processing · doi:10.1049/iet-spr.2019.0297 · Cited by 52
“The RCNN architecture involves using CNN [68] layers for feature extraction of input data combined with LSTMs [69] to support sequence prediction.”
MethodZiv, R., Dikopoltsev, A., Zahavy, T., Rubinstein, I., Sidorenko, P., Cohen, O., & Segev, M. (2020) · Optics Express · doi:10.1364/oe.383217 · Cited by 51
“This concept has been around for some time now [20], but only in recent years, with the exponential growth in computational power and improved network architectures [21], deep networks are proving to be a formidable technique that can solve difficult and complex problems.”
BackgroundCancelable face and iris recognition system based on deep learning
Abdellatef, E., Soliman, R. F., Omran, E. M., Ismail, N. A., Abdulrahman, S. E. S. E., Ismail, K. N., Rihan, M., Amin, M. A., Eisa, A. A., & El‐Samie, F. E. A. (2022) · Optical and Quantum Electronics · doi:10.1007/s11082-022-03770-0 · Cited by 51
“For the current architecture, Rectified Linear Unit (ReLU) (LeCun et al. 2010) is applied as the activation function.”
Method(2019) · Multimedia Research · doi:10.46253/j.mr.v2i3.a2 · Cited by 51
“A usually exploited filter is the discrete Gaussian filter G fl [14], which is used for smoothing, exhibited using eq.”
MethodPruneski, J. A., Pareek, A., Nwachukwu, B. U., Martin, R. K., Kelly, B. T., Karlsson, J., Pearle, A. D., Kiapour, A. M., & Williams, R. J. (2023) · Knee Surgery, Sports Traumatology, Arthroscopy · doi:10.1007/s00167-022-07272-0 · Cited by 50
“From the mid-century Turing machine used to decrypt German messages, to the recurrent neural networks (RNN) and convolutional neural networks (CNN) developed during the latter half of the century, techniques have progressively built upon each other and become increasingly powerful in understanding and interpreting hum…”
BackgroundA Review of Computer-Aided Expert Systems for Breast Cancer Diagnosis
Liew, X. Y., Hameed, N., & Clos, J. (2021) · Cancers · doi:10.3390/cancers13112764 · Cited by 51
“An example of a standard CNN model architecture with two feature stages is shown below in Figure 13 [134].”
MethodDu, X., Jia, W., Yu, P., Shi, Y., & Cheng, S. (2022) · Measurement · doi:10.1016/j.measurement.2022.111782 · Cited by 50
Deep faster R-CNN-based automated detection and localization of multiple types of damage
Suh, G., & Cha, Y. (2018) · Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems · doi:10.1117/12.2295954 · Cited by 50
Fractional Wavelet Scattering Network and Applications
Liu, L., Wu, J., Li, D., Senhadji, L., & Shu, H. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2850356 · Cited by 50
“deep convolution networks usually have learning filters to take into account these unknown variabilities [45].”
Vehicle Type Classification Using Convolutional Neural Network
Hicham, B., Azough, A., & Mohammed, M. (2018) · IEEE Congress on Information Science and Technology (CiSt) · doi:10.1109/cist.2018.8596500 · Cited by 50
“These layers result in an output specifying the class, or classes to which the image belongs [16].”
BackgroundInfluentialToward the Next Generation of Retinal Neuroprosthesis: Visual Computation with Spikes
Yu, Z., Liu, J. K., Jia, S., Zhang, Y., Zheng, Y., Tian, Y., & Huang, T. (2020) · Engineering · doi:10.1016/j.eng.2020.02.004 · Cited by 51
Deep learning for camera data acquisition, control, and image estimation
Brady, D. J., Fang, L., & Ma, Z. (2020) · Advances in Optics and Photonics · doi:10.1364/aop.398263 · Cited by 51
Machine learning based fast forward modelling of ground-based time-domain electromagnetic data
Bording, T. S., Asif, M. R., Barfod, A. A. S., Larsen, J. J., Zhang, B., Grombacher, D., Christiansen, A. V., Engebretsen, K. W., Pedersen, J. B., Maurya, P. K., et al. (2021) · Journal of Applied Geophysics · doi:10.1016/j.jappgeo.2021.104290 · Cited by 50
“Neural networks are widely used for a range of applications across science and engineering in computer vision (LeCun et al., 2010), healthcare (Alloghani et al.”
BackgroundConvolutional neural networks applied to high-frequency market microstructure forecasting
Doering, J., Fairbank, M., & Markose, S. M. (2017) · Computer Science and Electronic Engineering Conference · doi:10.1109/ceec.2017.8101595 · Cited by 50
“A CNN is a specific type of neural network which has been proven to be especially successful at classifying noisy datasets such as images and speech [11], [12].”
BackgroundSemi-supervised learning with convolutional neural networks for UAV images automatic recognition
Amorim, W. P., Tetila, E. C., Pistori, H., & Papa, J. P. (2019) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2019.104932 · Cited by 49
Banharnsakun, A. (2018) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-018-0811-z · Cited by 48
“8 refers to a simple CNN structure (LeNet-5) [39].”
BackgroundMultiscale road centerlines extraction from high-resolution aerial imagery
Liu, R., Miao, Q., Song, J., Quan, Y., Li, Y., Xu, P., & Dai, J. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.10.036 · Cited by 48
Strengthen user authentication on mobile devices by using user’s touch dynamics pattern
Teh, P. S., Zhang, N., Tan, S., Shi, Q., Khoh, W. H., & Nawaz, R. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01654-y · Cited by 48
“These techniques have been widely used in the field of computer vision to automatically extract representative features from image related data (LeCun et al. 2010; Xu et al. 2014; Sun et al. 2014).”
MethodJagannath, J., Jagannath, A., Furman, S., & Gwin, T. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-77939-9_2 · Cited by 48
A New Channel Boosted Convolutional Neural Network using Transfer LearningPreprint
Khan, A., Sohail, A., & Ali, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.08528 · Cited by 48
“The interesting work of LeCun et al. [3] brought CNNs in limelight.”
BackgroundLaRED: a large RGB-D extensible hand gesture dataset
Hsiao, Y.-S., Sànchez-Riera, J., Lim, T., Hua, K., & Cheng, W.-H. (2014) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/2557642.2563669 · Cited by 47
“In particular, the method used is the convolutional neural network (CNN) explained in [4], and the implementation used can be found in [9].”
MethodArtificial neural network for bubbles pattern recognition on the images
Poletaev, I., Pervunin, K. S., & Tokarev, M. P. (2016) · Journal of Physics Conference Series · doi:10.1088/1742-6596/754/7/072002 · Cited by 47
Jayalakshmi, G. S., & Kumar, V. S. (2019) · International Conference on Computational Intelligence in Data Science (ICCIDS) · doi:10.1109/iccids.2019.8862143 · Cited by 47
“For an input feature map , with filter of kernel/weight matrix and bias , the output feature map is calculated by convolution operation of weight matrix over the input feature as follows [14],”
MethodJia, X., Yang, J., Liu, R., Wang, X., Cotöfană, S., & Zhao, W. S. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2987760 · Cited by 47
Graph neural networks in TensorFlow-Keras with RaggedTensor representation (kgcnn)
Reiser, P., Eberhard, A., & Friederich, P. (2021) · Software Impacts · doi:10.1016/j.simpa.2021.100095 · Cited by 47
Wamriew, D. S., Charara, M., & Pissarenko, D. (2021) · Computers & Geosciences · doi:10.1016/j.cageo.2021.104965 · Cited by 47
A comparison of hybrid deep learning models for pneumonia diagnosis from chest radiograms
Sourab, S. Y., & Kabir, M. A. (2022) · Sensors International · doi:10.1016/j.sintl.2022.100167 · Cited by 47
Centrifugal Pump Fault Diagnosis Based on a Novel SobelEdge Scalogram and CNN
Zaman, W., Ahmad, Z., Siddique, M., Ullah, N., & Kim, J.-M. (2023) · Sensors · doi:10.3390/s23115255 · Cited by 47
“Feature maps are sets of matrices that are used as the input and output of each layer [39].”
BackgroundMethodObject Recognition Using Deep Neural Networks: A SurveyPreprint
Goyal, S., & Benjamin, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.3684 · Cited by 47
Handling dropout probability estimation in convolution neural networks using meta-heuristics
de Rosa, G. H., Papa, J. P., & Yang, X.-S. (2017) · Soft Computing · doi:10.1007/s00500-017-2678-4 · Cited by 46
“Therefore, the great question to be answered by researchers in this area concerns how human beings and animals basically learn by looking around (LeCun et al. 2010).”
BackgroundSingle-Stream CNN With Learnable Architecture for Multisource Remote Sensing Data
Yang, Y., Zhu, D., Qu, T., Wang, Q., Ren, F., & Cheng, C. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3169163 · Cited by 46
“convolutional neural network (CNN) [11] is a DL based model that significantly outperforms traditional methods in image classification and segmentation.”
MethodBig data-enabled multiscale serviceability analysis for aging bridges☆
Liang, Y., Wu, D., Liu, G., Li, Y., Gao, C., John, Z., & Wu, W. (2016) · Digital Communications and Networks · doi:10.1016/j.dcan.2016.05.002 · Cited by 46
“A Deep Convolutional Neural Network (DCNN) [38] is used to learn from visual media such as video and images because it demonstrates superior performance (high accuracy and fast training speed) on matrix-oriented featurelearning.”
MethodA survey of neural network accelerators
Li, Z., Wang, Y., Zhi, T., & Chen, T. (2017) · Frontiers of Computer Science · doi:10.1007/s11704-016-6159-1 · Cited by 46
“Moreover, a pooling layer has no parameter to learn because of its special operation, and is previously suggested to perform a non-linear active function but not now [29, 30].”
BackgroundStereo Vision-Based Object Recognition and Manipulation by Regions with Convolutional Neural Network
Du, Y., Muslikhin, M., Hsieh, T.-H., & Wang, M. (2020) · Electronics · doi:10.3390/electronics9020210 · Cited by 46
Circuits and Architectures for In-Memory Computing-Based Machine Learning Accelerators
Ankit, A., Chakraborty, I., Agrawal, A., Ali, M., & Roy, K. (2020) · IEEE Micro · doi:10.1109/mm.2020.3025863 · Cited by 46
“Convolutional neural networks (CNNs) adopt such convolutional operations for image processing applications.(12) Such layers are also separated by pooling and local response or contrast normalization layers.”
BackgroundEarly Risk Prediction of Diabetes Based on GA-Stacking
Tan, Y., Chen, H. H., Zhang, J., Tang, R., & Liu, P. (2022) · Applied Sciences · doi:10.3390/app12020632 · Cited by 46
Larraondo, P., Renzullo, L. J., Inza, I., & Lozano, J. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.10274 · Cited by 46
“Convolutional Neural Networks (CNN’s) [16] contain a series of layers which perform convolution operations, extracting the spatial information of input images.”
BackgroundSoftware defect prediction via optimal trained convolutional neural network
Balasubramaniam, S., & Gollagi, S. G. (2022) · Advances in Engineering Software · doi:10.1016/j.advengsoft.2022.103138 · Cited by 45
Tracking with deep neural networks
Jin, J., Dündar, A., Bates, J., Farabet, C., & Culurciello, E. (2013) · Conference on Information Sciences and Systems · doi:10.1109/ciss.2013.6552287 · Cited by 45
“In this work, we use a Convolutional Neural Network (ConvNet) [19] with filter banks trained by different training methods.”
MethodSelf-citationA review on Deep Learning approaches in Speaker Identification
Tirumala, S. S., & Shahamiri, S. R. (2016) · International Conference on Signal Processing Systems (ICSPS) · doi:10.1145/3015166.3015210 · Cited by 45
“Deep Belief Networks (DBN) proposed by Hinton in 2006 [16] has multiple interconnected hidden layers whereeach layer acting as an input to the next layer and is visible only to the next layer.”
BackgroundActivity-aware essential tremor evaluation using deep learning method based on acceleration data
Zheng, X., Vieira, A., Marcos, S. L., Aladro, Y., & Ordieres-Meré, J. B. (2018) · Parkinsonism & Related Disorders · doi:10.1016/j.parkreldis.2018.08.001 · Cited by 45
Ayachi, R., Said, Y., & Atri, M. (2020) · Big Data · doi:10.1089/big.2019.0093 · Cited by 45
Sensor Fusion Basketball Shooting Posture Recognition System Based on CNN
Fan, J., Bi, S., Wang, G., Zhang, L., & Sun, S. (2021) · Journal of Sensors · doi:10.1155/2021/6664776 · Cited by 45
Lavitt, F., Rijlaarsdam, D. J., van der Linden, D., Węglarz‐Tomczak, E., & Tomczak, J. M. (2021) · Applied Sciences · doi:10.3390/app11114912 · Cited by 45
“Because their architecture is intrinsically hierarchical, CNNs can automatically and adaptively learn multi-level hierarchies of features that are translationequivariant [61].”
BackgroundAbdul, W. (2020) · International Conference on Developments in eSystems Engineering (DeSE) · doi:10.1109/dese51703.2020.9450778 · Cited by 45
“Training is carried out with the help of a type of stochastic gradient descent algorithm to reduce the difference between the desired output and the network output [21].”
BackgroundTudose, A. M., Picioroaga, I. I., Sidea, D. O., Bulac, C., & Boicea, V. A. (2021) · Energies · doi:10.3390/en14134046 · Cited by 45
“CNNs display state-of-the-art performance on a wide variety of applications in the image processing field, such as recognition of handwritten text [37], object detection [38], or diagnosis based on medical images [39], as well as in other fields, such as speech recognition [40] or traffic forecasting…”
BackgroundSouli, S., & Lachiri, Z. (2017) · Applied Acoustics · doi:10.1016/j.apacoust.2017.08.002 · Cited by 45
A Review of Applications of Artificial Intelligence in Heavy Duty Trucks
Katreddi, S., Kasani, S. P. K., & Thiruvengadam, A. (2022) · Energies · doi:10.3390/en15207457 · Cited by 44
Hybrid Classifier Model for Big Data by leveraging Map reduce framework
Prasad, A. V. K., Venkat Dass, M., Reddy, K. S., Ramulu, S., & Prasad, K. R. (2023) · International Journal of Data Mining Modelling and Management · doi:10.1504/ijdmmm.2024.136219 · Cited by 46
Human action recognition using support vector machines and 3D convolutional neural networks
Latah, M. (2017) · International Journal of Advances in Intelligent Informatics · doi:10.26555/ijain.v3i1.89 · Cited by 44
“Pooling layer The goal of the pooling layer is to reduce the spatial size of the representation which is more robust to small variations in the location of features in the previous layer [35].”
BackgroundKrig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_2 · Cited by 45
Cognitive Workload Detection from Raw EEG-Signals of Vehicle Driver using Deep Learning
Almogbel, M. A., Dang, A. H., & Kameyama, W. (2019) · International Conference on Advanced Communication Technology · doi:10.23919/icact.2019.8702048 · Cited by 44
“One of the major advantages of deep neural networks is the ability to extract, learn and generalize features without preprocessing [22].”
BackgroundInterest Point Detector and Feature Descriptor Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_6 · Cited by 45
Automated Cell Counts on Tissue Sections by Deep Learning and Unbiased Stereology
Alahmari, S. S., Goldgof, D. B., Hall, L., Phoulady, H. A., Patel, R. H., & Mouton, P. R. (2018) · Journal of Chemical Neuroanatomy · doi:10.1016/j.jchemneu.2018.12.010 · Cited by 44
Emotion recognition using multi-scale EEG features through graph convolutional attention network
Cao, L., Zhao, W., & Sun, B. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.107060 · Cited by 43
Bourriz, M., Hajji, H., Laamrani, A., Bouanani, N. E., Abdelali, H. A., Bourzeix, F., El-Battay, A., Amazirh, A., & Chehbouni, A. (2025) · Remote Sensing · doi:10.3390/rs17091574 · Cited by 43
Wen, B., Wang, C., Li, K., Han, P., Holt, M. V., Savage, S. R., Lei, J. T., Dou, Y., Shi, Z., Li, Y., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02797-x · Cited by 44
A Survey on Supervised Convolutional Neural Network and Its Major Applications
Mane, D., & Kulkarni, U. V. (2017) · International Journal of Rough Sets and Data Analysis · doi:10.4018/ijrsda.2017070105 · Cited by 43
Deep Architectures for Modulation RecognitionPreprint
West, N., & O’Shea, T. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.09197 · Cited by 43
“menting these filters, such as polyphase filterbanks, typically provide ways to reduce the width of filters for computational or latency reasons. The transfer function for a standard convolutional layer [9] is given below in equation 3, where y i is the output feature map for the ith filter, b and k represent learned bias…”
BackgroundFull-Waveform Inversion Using a Learned Regularization
Sun, P., Yang, F., Liang, H., & Ma, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3322964 · Cited by 42
“Convolutional neural networks (CNNs) [16] are the prime candidates contributing to the exploration of data-driven priors, which has led to their wide application in FWI.”
BackgroundLow Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks
Garland, J., & Gregg, D. (2017) · IEEE Computer Architecture Letters · doi:10.1109/lca.2017.2656880 · Cited by 42
“F”
Extracting region of interest for palmprint by convolutional neural networks
Bao, X., & Guo, Z. (2016) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2016.7820994 · Cited by 43
“Over recent years, the landscape of computer vision has been drastically altered and pushed forward through a fast, efficient, endto-end learning framework, the Convolutional Neural Network (CNN) [12].”
BackgroundGuo, Z., Shen, M., Duan, L., Zhou, Y., Xiang, J., Ding, H., Chen, S., Deußen, O., & Guo, D. (2017) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2017.7950486 · Cited by 42
“The features extracted from deep ConvNets are very effective in many image recognition and classification problems [14].”
MethodVideo Representation Learning for CCTV-Based Violence Detection
Ditsanthia, E., Pipanmaekaporn, L., & Kamonsantiroj, S. (2018) · Technology Innovation Management and Engineering Science International Conference (TIMES-iCON) · doi:10.1109/times-icon.2018.8621751 · Cited by 42
“Motivated by the great success of deep convolution neural networks in computer vision [1, 2, 8-9], we propose a novel deep learning approach to video-based violence detection.”
BackgroundSiar, H., & Teshnehlab, M. (2019) · Iranian Joint Congress on Fuzzy and Intelligent Systems · doi:10.1109/cfis.2019.8692148 · Cited by 42
“One of the powerful types of deep neural networks is the convolution neural network inspired by the biological processes of the cat’s vision cortex [6] [7].”
BackgroundMalware visualization methods based on deep convolution neural networks
Ren, Z., Chen, G., & Lu, W. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08310-9 · Cited by 42
“In terms of image recognition, there are various successful technologies, such as deep neural networks, especially the famous convolution neural networks (CNN) [16, 26].”
BackgroundApostolopoulos, I. D., Pintelas, E. G., Livieris, I. E., Apostolopoulos, D. J., Papathanasiou, N. D., Pintelas, P., & Panayiotakis, G. (2021) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-021-02378-y · Cited by 42
“Deep Learning, and more specifically, Convolutional Neural Networks (CNN) [5], alludes to a wide class of Machine Learning methods and structures, utilizing large amount of data.”
BackgroundUsing Deep Learning to Fill Data Gaps in Environmental Footprint Accounting
Zhao, B., Shuai, C., Qu, S., & Xu, M. (2022) · Environmental Science & Technology · doi:10.1021/acs.est.2c01640 · Cited by 42
Convolution, attention and structure embeddingPreprint
Andreoli, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01289 · Cited by 42
“Convolution is a powerful operator, which is widely used in deep neural networks in many different flavours: [13, 12, 8, 6, 9, 18, 15].”
A comparison of 1D and 2D LSTM architectures for the recognition of handwritten Arabic
Yousefi, M. R., Soheili, M. R., Breuel, T. M., & Stricker, D. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2075930 · Cited by 41
On line emotion detection using retrainable deep neural networks
Kollias, D., Tagaris, A., & Stafylopatis, A. (2016) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2016.7850049 · Cited by 41
“Recently, big interest has been paid to deep learning techniques and neural networks [7-9] in various application areas, including speech analysis [10-13], natural language processing [14] and image analysis and recognition [15-19].”
BackgroundFeedback weight convolutional neural network for gait recognition
Wu, H., Weng, J., Chen, X., & Lu, W. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.06.019 · Cited by 41
Lung Nodule Classification Using Deep ConvNets on CT Images
Sathyan, H., & Vinitha Panicker, J. (2018) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt.2018.8494084 · Cited by 41
“In this work we concentrate on the classification of lung nodules [7] in to three classes such as non-nodule, nodule of size less than 3 mm and nodule of size greater than or equal to 3 mm using deep convolutional neural networks (CNN) [3] along with reduced false positive rate.”
MethodThrough the looking glass: Seeing events in power systems dynamics
Miranda, V., Cardoso, P. A., Bessa, R. J., & Decker, I. (2018) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2018.10.024 · Cited by 41
Remote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space
Wu, M., Jin, X., Jiang, Q., Lee, S., Liang, W., Guo, L., & Yao, S. (2020) · The Visual Computer · doi:10.1007/s00371-020-01933-2 · Cited by 42
“The first two contrast methods include two types of machine learning-based methods; one method utilizes the deep neural network exploiting both low-level and semantic representations for image colorization [51], and another model is based on CNN combining both global priors and local image features for image colorizati…”
MethodInfluentialFan, Z., Jamil, M., Sadiq, M. T., Huang, X., & Yu, X. (2020) · Journal of Healthcare Engineering · doi:10.1155/2020/8889412 · Cited by 41
“Convolutional neural network (CNN), which is a type of deep learning, uses the images to train deep models and clas-sifies them based on output categories [19].”
BackgroundKumar, K. E. N., & Uma, V. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-03709-4 · Cited by 41
“csv dataset FPR Training data in % GA [30] SVM [31] CNN [32] LSTM [33] NN [27] SLnO + NN [26] SI-SLnO”
MethodInfluentialAutomatic guava disease detection using different deep learning approaches
Tewari, V., Azeem, N. A., & Sharma, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15909-6 · Cited by 41
“[17] ResNets have proven themselves useful in biomedical image classification [27].”
Convolutional Feature Learning and CNN Based HMM for Arabic Handwriting Recognition
Amrouch, M., Rabi, M., & Es-Saady, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-94211-7_29 · Cited by 41
A Multi-View Human Action Recognition System in Limited Data Case using Multi-Stream CNN
Chenarlogh, V. A., Razzazi, F., & Mohammadyahya, N. (2019) · Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) · doi:10.1109/icspis48872.2019.9066079 · Cited by 40
“Because of fewer connections in this layer, CNNs are trained faster than other neural networks [11].”
BackgroundAfsharpour, P., Zoughi, T., Deypir, M., & Zoqi, M. J. (2024) · Frontiers in Plant Science · doi:10.3389/fpls.2024.1366395 · Cited by 40
Deep Learning for Quantified Gait Analysis: A Systematic Literature Review
Khan, A., C., O. A. G., Garcia-Salicetti, S., & Vigneron, V. (2024) · IEEE Access · doi:10.1109/access.2024.3434513 · Cited by 40
Research on Large-scale Structured and Unstructured Data Processing based on Large Language Model
Li, B., Jiang, G., Li, N., & Song, C. (2024) · International Conference on Machine Learning, Pattern Recognition and Automation Engineering (MLPRAE) · doi:10.1145/3696687.3696707 · Cited by 40
“An encoder is a traditional sequence-to-sequence structure that works by using an encoder to encode a sequence of source languages into an intermediate vector, which is then decoded into a sequence of target languages using a decoder [ 7 ] .”
Deep learning-based remote sensing retrieval of inland water quality: A review
Pang, Z., Zhou, Z., Fu, J., Jiang, W., Qin, X., & Sun, M. (2025) · Journal of Hydrology Regional Studies · doi:10.1016/j.ejrh.2025.102759 · Cited by 40
Evolving deep neural networks: A new prospect
Tirumala, S. S., Ali, S. S. A., & Ramesh, C. P. (2016) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/fskd.2016.7603153 · Cited by 40
“Deep learning showed considerable success in Nature language processing, image recognition and other patter recognition implementations [2]”
BackgroundParticle swarm optimization for deep learning of convolution neural network
Khalifa, M. H., Ammar, M., Ouarda, W., & Alimi, A. M. (2017) · doi:10.1109/sccsit.2017.8293059 · Cited by 40
Bhatt, J. S., Joshi, M. V., & Sharma, M. (2018) · International Conference on Machine Vision · doi:10.1117/12.2309530 · Cited by 40
“CNNs are biologically-inspired trainable architectures that can learn multi-level hierarchies of features [18].”
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.