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 701–800 of 1,001
Heart disease prediction using convolutional neural network
Sharma, A. K., Pal, T., & Jaiswal, V. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-822706-0.00012-3 · Cited by 32
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_2 · Cited by 32
Oil Palm Fruit Ripeness Detection using Deep Learning
Ashari, S., Yanris, G. J., & Purnama, I. (2022) · SinkrOn · doi:10.33395/sinkron.v7i2.11420 · Cited by 32
Detection of Litchi Leaf Diseases and Insect Pests Based on Improved FCOS
Xie, J., Zhang, X., Liu, Z., Liao, F., Wang, W., & Li, J. (2023) · Agronomy · doi:10.3390/agronomy13051314 · Cited by 32
Wybo, W. A. M., Tsai, M. C., Tran, V. A., Illing, B., Jordan, J., Morrison, A., & Senn, W. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2300558120 · Cited by 32
“5A), which by design features localized receptive fields adapted for visual processing (59).”
BackgroundPolSAR image classification based on multi-scale stacked sparse autoencoder
Zhang, L., Jiao, L., Ma, W., Duan, Y., & Zhang, D. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.03.024 · Cited by 32
Vision-Based Obstacle Avoidance for UAVs via Imitation Learning with Sequential Neural Networks
Park, B., & Oh, H. (2020) · International Journal of Aeronautical and Space Sciences · doi:10.1007/s42405-020-00254-x · Cited by 32
“In addition to FCNNs, convolutional neural networks (CNNs) are a type of neural network that [17] do not have fully connected nodes among each layer.”
BackgroundParking Lot Occupancy Detection Using Hybrid Deep Learning CNN-LSTM Approach
Hùng, B. T., & Chakrabarti, P. (2022) · Algorithms for intelligent systems · doi:10.1007/978-981-16-6332-1_43 · Cited by 31
The Deep Convolutional Neural Network Role in the Autonomous Navigation of Mobile Robots (SROBO)
Esfahlani, S. S., Sanaei, A., Ghorabian, M., & Shirvani, H. (2022) · Remote Sensing · doi:10.3390/rs14143324 · Cited by 31
“In the feedforward multilayered ranked CNNs, each layer employs convolutional kernels to execute numerous conversions [15].”
Othman, E., Werner, P., Saxen, F., Al-Hamadi, A. K., Gruss, S., & Walter, S. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103743 · Cited by 31
Road Damage Detection using YOLO with Image Tiling about Multi-source Images
Jeong, D., & Kim, J. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020282 · Cited by 31
“And through the Convolutional Neural Network (CNN) [21], the input data size reduced by 1/2, and feature maps are learned based on the layer’s width, height, and channel.”
MethodVariational inference of ice shelf rheology with physics-informed machine learning
Riel, B. V., & Minchew, B. (2023) · Journal of Glaciology · doi:10.1017/jog.2023.8 · Cited by 31
RETRACTED ARTICLE: Control learning rate for autism facial detection via deep transfer learning
Mouatasim, A. E., & Ikermane, M. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02598-9 · Cited by 31
“1 Applied Mathematics and Computation Science (AMCS) Group, Faculty of Polydisciplinary Ouarzazate (FPO), Ibnou Zohr University, 45800 Ouarzazate, Morocco shown great promise in the field of image classification [11, 15, 20, 21].”
BackgroundRetractedWang, J., Jaboyedoff, M., Chen, G., Luo, X., Derron, M., Hu, Q., Fei, L., Prajapati, G., Choanji, T., Luo, S., et al. (2023) · Landslides · doi:10.1007/s10346-023-02141-4 · Cited by 31
“Landslide susceptibility prediction model The Convolutional Neural Network (CNN) is widely used in image processing but struggle to consider the influence of previous input images on the current image due to their feedforward architecture (LeCun et al. 1998; Yann et al. 2010).”
Gul, S., & Khan, M. S. (2023) · IEEE Access · doi:10.1109/access.2023.3344813 · Cited by 31
Anthes, G. (2013) · Communications of the ACM · doi:10.1145/2461256.2461262 · Cited by 31
Implementation of evolutionary algorithms for deep architectures
Tirumala, S. S. (2014) · Unitec Research Bank (Unitec Institute of Technology) · Cited by 31
Image-Specific Classification With Local and Global Discriminations
Zhang, C., Cheng, J., Li, C., & Tian, Q. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2748952 · Cited by 31
“As to the CNN-based image representation, we use the code provided in [46] with seven layers networks.”
MethodInfluentialExploring convolutional neural networks and topic models for user profiling from drug reviews
Tutubalina, E. V., & Nikolenko, S. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5336-z · Cited by 31
“CNNs are a natural fit for image processing, commonly applied to such problems as image classification and recognition, character recognition, image segmentation and object recognition, scene labeling, video processing, and so on [39, 54].”
BackgroundJodeiri, A., Zoroofi, R. A., Hiasa, Y., Takao, M., Sugano, N., Sato, Y., & Otake, Y. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105282 · Cited by 31
SeizureNet: a model for robust detection of epileptic seizures based on convolutional neural network
Zhao, W., & Wang, W. (2020) · Cognitive Computation and Systems · doi:10.1049/ccs.2020.0011 · Cited by 32
“The CNN [24] is one of the most popular algorithms for deep learning.”
BackgroundSurvey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet?Preprint
Lavi, B., Ullah, I., Fatan, M., & Rocha, A. D. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.00355 · Cited by 31
“Deep-learning (DL) models – e.g.,convolutional neural networks (CNNs) [8, 9, 10]– have been particularly used to solve the problem of PReID by learning from data.”
MethodTowards Real-Time People Recognition on Aerial Imagery Using Convolutional Neural Networks
de Oliveira, D. C., & Wehrmeister, M. A. (2016) · IEEE International Symposium on Real-Time Distributed Computing (ISORC) · doi:10.1109/isorc.2016.14 · Cited by 30
“Thus, features extractors are constructed based on training, manipulating the input data to perform the classification task [24].”
BackgroundMethodDeepPod: a convolutional neural network based quantification of fruit number in Arabidopsis
Hamidinekoo, A., Garzón-Martínez, G. A., Ghahremani, M., Corke, F. M. K., Zwiggelaar, R., Doonan, J. H., & Lü, C. (2020) · GigaScience · doi:10.1093/gigascience/giaa012 · Cited by 30
Barua, A., Zhang, Z., Al-Turjman, F., & Yang, X. (2020) · IEEE Access · doi:10.1109/access.2020.3000599 · Cited by 30
“To know more about CNN and its layers, readers can follow [75]–[79] works of literature.”
BackgroundAn Edge 3D CNN Accelerator for Low-Power Activity Recognition
Wang, Y., Wang, Y., Shi, C., Cheng, L., Li, H., & Li, X. (2020) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2020.3011042 · Cited by 30
“In recent years, a plenty of specialized accelerator architectures have been introduced to accelerate the computation-intensive CNN inference for either mobile or cloud application scenarios [13], [14], [19], [31], [32].”
BackgroundOptimization Assisted Convolutional Neural Network for Facial Emotion Recognition
Sarkar, A. (2020) · Multimedia Research · doi:10.46253/j.mr.v3i2.a5 · Cited by 30
“The extracted feature B f is supplied as an input to optimized CNN for optimal weight tuning [20].”
MethodBang, H., Min, J., & Jeon, H. (2021) · Sensors · doi:10.3390/s21082759 · Cited by 30
“The layers of CNN are a convolutional layer, an activation layer, a pooling layer, a fully connected layer, and a softmax layer [11].”
BackgroundPrecise Identification of Prostate Cancer from DWI Using Transfer Learning
Abdelmaksoud, I. R., Shalaby, A. M., Mahmoud, A. H., Elmogy, M. M., Aboelfetouh, A., El‐Ghar, M. A., El-Melegy, M., Alghamdi, N. S., & El-Baz, A. S. (2021) · Sensors · doi:10.3390/s21113664 · Cited by 30
“This reduction simplifies and expedites the training process of CNNs [37,38].”
BackgroundOptimizing image-based deep learning for energy geoscience via an effortless end-to-end approach
Koeshidayatullah, A. (2022) · Journal of Petroleum Science and Engineering · doi:10.1016/j.petrol.2022.110681 · Cited by 30
RUL prediction based on GAM–CNN for rotating machinery
Du, X., Jia, W., Yu, P., Shi, Y., & Gong, B. (2023) · Journal of the Brazilian Society of Mechanical Sciences and Engineering · doi:10.1007/s40430-023-04062-8 · Cited by 30
“19, 20, 21, 22.”
BackgroundDeep convolutional neural networks based on semi-discrete frames
Wiatowski, T., & Bölcskei, H. (2015) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2015.7282648 · Cited by 30
“Spectacular success in many practical classification tasks has been reported for feature extractors generated by deep convolutional neural networks [4], [5].”
Feature adapted convolutional neural networks for downbeat tracking
Durand, S., Bello, J. P., David, B., & Gaël Richard, A. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471684 · Cited by 30
“We will describe each network, illustrated in figure 1, and their input computation in more details below.”
MethodLi, J., Zhang, R., & Li, Y. (2016) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2016.7729230 · Cited by 30
Unsupervised Deep Haar Scattering on GraphsPreprint
Chen, X., Cheng, X., & Mallat, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.2390 · Cited by 30
“53%, [5]), and scattering networks with Gabor wavelet (0.”
BackgroundMethodBeyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks
Zhang, C., Cheng, J., Liu, J., Pang, J., Huang, Q., & Tian, Q. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2485783 · Cited by 29
“LeCun et al. [33] used convolutional networks while Zeiler et al. [34] proposed deconvolutional networks for visual applications.”
BackgroundMultiplication-free Neural Networks
Akbaş, C. E., Bozkurt, A., Çetin, A. E., Çetin-Atalay, R., & Üner, A. (2015) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2015.7130369 · Cited by 29
Towards Feature-free TSP Solver Selection: A Deep Learning Approach
Zhao, K., Liu, S., Yu, J. X., & Rong, Y. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533538 · Cited by 30
Deep learning model for detection of COVID-19 utilizing the chest X-ray images
Gafoor, S. A., Sampathila, N., Madhushankara, M., & Swathi, K. S. (2022) · Cogent Engineering · doi:10.1080/23311916.2022.2079221 · Cited by 29
Surendhar, S. P. A., Kanna, R. K., & Indumathi, R. (2023) · SN Computer Science · doi:10.1007/s42979-023-01893-z · Cited by 29
“SN Computer Science 2% were suggested for biopsy [5].”
Cattle Brand Recognition using Convolutional Neural Network and Support Vector Machines
Silva, C., Welfer, D., Gioda, F. P., & Dornelles, C. (2017) · IEEE Latin America Transactions · doi:10.1109/tla.2017.7854627 · Cited by 29
“mat [13] LECUN, Y.”
Exploiting Parallelism for CNN Applications on 3D Stacked Processing-In-Memory Architecture
Wang, Y., Chen, W., Yang, J., & Li, T. (2018) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2018.2868062 · Cited by 29
“A CNN can be represented by a directed acyclic graph [12].”
MethodCompressing the Input for CNNs with the First-Order Scattering Transform
Oyallon, E., Belilovsky, E., Zagoruyko, S., & Valko, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01240-3_19 · Cited by 29
“Convolutional neural networks (CNNs) for supervised vision tasks learn often from raw images [1] that could be arbitrarily large.”
BackgroundHeryadi, Y., & Miranda, E. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-14132-5_15 · Cited by 29
Deep Latent Factor Model with Hierarchical Similarity Measure for recommender systems
Han, J., Zheng, L., Huang, H., Xu, Y., Yu, P. S., & Zuo, W. (2019) · Information Sciences · doi:10.1016/j.ins.2019.07.024 · Cited by 29
“In recent years, deep learning, as an effective technique extract expressive features, has been widely applied in many research areas, such as computer vision [19] , natural language processing [30] , etc.”
BackgroundIntelligent Diagnosis towards Hydraulic Axial Piston Pump Using a Novel Integrated CNN Model
Tang, S., Zhu, Y., Yuan, S., & Li, G. (2020) · Sensors · doi:10.3390/s20247152 · Cited by 29
“The pooling layer, namely down-sampling layer, is usually assigned after the convolutional layer to reduce the size of the input feature map and decrease the number of parameters in the network model [42,43].”
BackgroundSagayaraj, M. J., Jithesh, V., & Roshani, D. (2021) · International Conference on Artificial Intelligence and Smart Energy (ICAIS) · doi:10.1109/icais50930.2021.9395855 · Cited by 29
“In this study Long Short Term Memory Recurrent Neural Network (LSTM) [23] and Convolutional Neural Network (CNN) [24], are considered for HRRP based classification.”
MethodKhan, S. H., & Iqbal, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.16546 · Cited by 30
Khodabandehlou, H., Rashedi, M., Wang, T., Tulsyan, A., Schorner, G., Garvin, C., & Ündey, C. (2024) · Biotechnology and Bioengineering · doi:10.1002/bit.28646 · Cited by 28
“Multiple transformations and nonlinear activation functions are applied in CNN's convolution layers to extract useful features from different regions of input data (LeCun et al., 2010).”
MethodMachine learning in X-ray diffraction for materials discovery and characterization
Davel, C. M., Bassiri‐Gharb, N., & Correa‐Baena, J. (2025) · Matter · doi:10.1016/j.matt.2025.102272 · Cited by 28
Evolving deep neural networks using coevolutionary algorithms with multi-population strategy
Tirumala, S. S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04749-2 · Cited by 29
“The success of deep learning (DL) has enhanced the research prospects of machine learning (ML) producing state-of-the-art results in pattern recognition, natural language processing [1], speaker recognition [2], drug discovery [3], bioinformatics [4] and other implementations [5, 6].”
BackgroundMeta-Heuristic Based Deep Learning Model for Leaf Diseases Detection
Ruth, J. A., Uma, R. N., Meenakshi, A. V., & Ramkumar, P. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10880-z · Cited by 28
“It is utilized to identify the correct leaf disease based on the effective features [7].”
MethodDevelopment of a core feature identification application based on the Faster R-CNN algorithm
Jiang, Q., Jia, M., Bi, L., Zhuang, Z., & Gao, K. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105200 · Cited by 28
Multi-Sensors Space and Time Dimension Based Intrusion Detection System in Automated Vehicles
Wang, L., Zhang, X., Li, D., & Liu, H. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3306345 · Cited by 28
“The input and output of each layer are sets of feature maps [38].”
BackgroundSmart Medical Application of Deep Learning (MUNet) for Detection of COVID-19 from Chest Images
Smadi, A. A., Abugabah, A., Alsmadi, M. K., & Al-smadi, A. M. (2024) · Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications · doi:10.58346/jowua.2024.i1.010 · Cited by 28
Matray, V., Amlani, F., Feyel, F., & Néron, D. (2024) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2024.117243 · Cited by 28
Detection of coronary heart disease based on heart sound and hybrid Vision Transformer
Zhao, W., Ma, H., Jin, N., Zheng, Y., & Guo, X. (2024) · Applied Acoustics · doi:10.1016/j.apacoust.2024.110420 · Cited by 28
Autonomous Document Cleaning—A Generative Approach to Reconstruct Strongly Corrupted Scanned Texts
Dai, Z., & Lücke, J. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2313126 · Cited by 28
“In analogy to template matching ([5, 14] and many more) we refer to the result of the MAP estimate (15) as the match for the image patch, to ~x∗ as the matched position and to c∗ as the matched class.”
MethodLinear-nonlinear cascades capture synaptic dynamics
Rossbroich, J., Trotter, D., Beninger, J., Tóth, K., & Naud, R. (2021) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008013 · Cited by 28
“By optimizing the kernels k and weights w, similar CNNs have been trained to classify images [71, 72] as well as sounds [73, 74].”
Image-based identification of maydis leaf blight disease of maize (Zea mays) using deep learning
Haque, M. A., Marwaha, S., Arora, A., Paul, R. K., HOODA, K. S., Sharma, A., & Grover, M. (2021) · The Indian Journal of Agricultural Sciences · doi:10.56093/ijas.v91i9.116089 · Cited by 28
“The CNNs have the capability to automatically learn the pattern in the images that are invariant of translation such as shifting, distortion, scaling etc. and can mine feature hierarchies (LeCun et al. 2010).”
BackgroundThe State of the Art in Machine Learning-Based Digital Forensics
Oladipo, F. O., Ogbuju, E., Samson, A. F., & Musa, A. E. (2020) · International Journal of Computing and Artificial Intelligence · doi:10.33545/27076571.2021.v2.i1a.21 · Cited by 28
On the Engineering of AI-Powered Systems
Kusmenko, E., Pavlitskaya, S., Rumpe⋆, B., & Stüber, S. (2019) · IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW) · doi:10.1109/asew.2019.00042 · Cited by 27
“Many neural networks for image classification [10], [11] use a convolutional architecture.”
Backgroundda Silva, G. L. F., Diniz, P. S., Ferreira, J. L., França, J. V. F., Silva, A. C., de Paiva, A. C., & de Cavalcanti, E. A. A. (2020) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-020-02199-5 · Cited by 27
“The loss function was the cross entropy [35], and the weights update was based on the standard backpropagation algorithm [26] with a learning rate of 0.01.”
MethodInfluentialCompetition convolutional neural network for sleep stage classification
Zhang, J., & Wu, Y. X. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102318 · Cited by 27
Deep learning method for determining the surface elastic moduli of microstructured solids
Sang, Y., Huang, W.-Z., Li, M., & Feng, X. (2021) · Extreme Mechanics Letters · doi:10.1016/j.eml.2021.101226 · Cited by 27
Konnaris, M. A., Brendel, M., Fontana, M. A., Otero, M., Ivashkiv, L. B., Wang, F., & Bell, R. D. (2022) · Arthritis Research & Therapy · doi:10.1186/s13075-021-02716-3 · Cited by 27
Diagnosis of Intracranial Tumors via the Selective CNN Data Modeling Technique
Singh, V., Gourisaria, M. K., Harshvardhan, G. M., Rautaray, S. S., Pandey, M., Sahni, M., León‐Castro, E., & Espinoza-Audelo, L. F. (2022) · Applied Sciences · doi:10.3390/app12062900 · Cited by 27
Introduction to Machine Learning
(2020) · Cambridge University Press eBooks · doi:10.1017/9781108690935.003 · Cited by 27
Zhou, R., Zhang, Z., Zhai, T., Gu, X., Cao, H., Xiao, Z., & Li, L. H. Y. (2023) · Optics Express · doi:10.1364/oe.477309 · Cited by 27
Liu, B., Jin, Y., Feng, S., Yu, H., Zhang, Y., & Li, Y. (2023) · European Radiology · doi:10.1007/s00330-023-09713-x · Cited by 27
“Deep learning is associated with a promising diagnostic and information explanation ability [20-22].”
BackgroundSun, J., Xu, M., Ru, J., James-Bott, A., Xiong, D., Wang, X., & Cribbs, A. P. (2023) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2023.115500 · Cited by 27
Subject-independent EEG classification based on a hybrid neural network
Zhang, H., Ji, H., Yu, J. H., Li, J., Jin, L., Liu, L., Bai, Z., & Ye, C. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1124089 · Cited by 29
“In recent years, deep learning techniques have attracted significant attention for their success in computer vision, natural language processing (LeCun et al., 2010; Schmidhuber, 2015; Voulodimos et al., 2018; Nassif et al., 2019).”
BackgroundTschandl, P., Kittler, H., & Argenziano, G. (2017) · British Journal of Dermatology · doi:10.1111/bjd.15695 · Cited by 25
Multi-column Deep Neural Network for Offline Arabic Handwriting Recognition
Almodfer, R., Xiong, S., Mudhsh, M., & Duan, P. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-68612-7_30 · Cited by 27
Chauhan, S., & Ahmad, S. (2019) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.25763 · Cited by 27
A robust pathological voices recognition system based on DCNN and scattering transform
Souli, S., Amami, R., & Yahia, S. B. (2021) · Applied Acoustics · doi:10.1016/j.apacoust.2020.107854 · Cited by 27
Machine learning and its application in microscopic image analysis
Xing, F., & Yang, L. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-804076-8.00004-9 · Cited by 28
Misimi, E., Øye, E. R., Sture, Ø., & Mathiassen, J. R. (2017) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2017.05.021 · Cited by 27
“Of particular interest for vision-based applications are the so called Convolutional Neural Networks (CNNs), which are inspired by the visual cortex and subsequently tailored for computer vision (LeCun et al., 2010).”
BackgroundTowards Memory-Efficient Allocation of CNNs on Processing-in-Memory Architecture
Wang, Y., Chen, W., Yang, J., & Li, T. (2018) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2018.2791440 · Cited by 27
“Therefore, a CNN can be represented by a synchronous data flow graph or a directed acyclic graph [9], [10].”
Data-driven prediction of cylinder-induced unsteady wake flow
Li, S., Yang, J., & Teng, P. (2024) · Applied Ocean Research · doi:10.1016/j.apor.2024.104114 · Cited by 26
A Mobile Application for Dog Breed Detection and Recognition Based on Deep Learning
Sinnott, R., Wu, F., & Chen, W. (2018) · IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT) · doi:10.1109/bdcat.2018.00019 · Cited by 26
Galab, M. K., Taha, A., & Zayed, H. H. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-05401-4 · Cited by 26
“Deep learning (DL) is one of the best techniques that automatically extract features from raw data [20].”
BackgroundChen, H., Qiu, Y., Yin, D., Chen, J., Chen, X., Liu, S., & Liu, L. (2022) · The Crop Journal · doi:10.1016/j.cj.2021.12.011 · Cited by 26
YOLO Method Analysis and Comparison for Real-Time Human Face Detection
Pebrianto, W., Mudjirahardjo, P., & Pramono, S. H. (2022) · Electrical Power, Electronics, Communications, Controls and Informatics Seminar (EECCIS) · doi:10.1109/eeccis54468.2022.9902919 · Cited by 26
Cyber threat detection: Unsupervised hunting of anomalous commands (UHAC)
Kayhan, V. O., Agrawal, M., & Shivendu, S. (2023) · Decision Support Systems · doi:10.1016/j.dss.2023.113928 · Cited by 26
Liu, G., Zhang, R., Hang, R., Ge, L., Shi, C., & Liu, Q. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3239109 · Cited by 26
“Deep learning is an advanced machine learning algorithm, which has achieved excellent performance in various image processing tasks, such as semantic segmentation, classification, and object detection [23], [24], [25], [26], [27].”
MethodStephen, O., & Sain, M. (2023) · Journal of Healthcare Engineering · doi:10.1155/2023/4597445 · Cited by 27
“Ten, a max-pooling operation picks the largest pixel values from a specifc part of the image kernels, thereby minimising the required parameters to be computed and making the convolution activities translational invariant to scale, size, and shape [31].”
BackgroundDeep Learning for Natural Language Processing: A Survey
Arkhangelskaya, E. O., & Nikolenko, S. (2023) · Journal of Mathematical Sciences · doi:10.1007/s10958-023-06519-6 · Cited by 27
“Convolutional neural networks are a natural fit for image processing and have long been applied to such problems as image classification and recognition, character recognition, image segmentation and object recognition, scene labeling, video processing, and so on; see, e.g., [179, 247].”
BackgroundMultimodal autism detection: Deep hybrid model with improved feature level fusion
Vidivelli, S., Padmakumari, P., & Shanthi, P. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108492 · Cited by 26
Image classification based on convolutional neural networks with cross-level strategy
Liu, Y., Yin, B., Yu, J., & Wang, Z. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3540-x · Cited by 26
An Automatic System for Smile Recognition Based on CNN and Face Detection
Qu, D., Huang, Z. R., Gao, Z., Zhao, Y., Zhao, X., & Song, G. (2018) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2018.8665310 · Cited by 26
“Input images are firstly mapped to the feature maps, which is followed by the process of pooling, and finally, the feature maps are converted to a vector, which is then used as an input of a fully connected neural network[11].”
BackgroundMethodInfluentialLi, X., Zhou, K., Xue, F., Chen, Z., Ge, Z., Chen, X., & Song, K. (2020) · Processes · doi:10.3390/pr8111480 · Cited by 26
“Correspondingly, CNN consists of a data input layer, convolutional layers, pooling layers, a fully connected layer and an output layer [12].”
BackgroundRecurrent neural network pruning using dynamical systems and iterative fine-tuning
Chatzikonstantinou, C., Konstantinidis, D., Dimitropoulos, K., & Daras, P. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.07.001 · Cited by 26
Violent Video Detection by Pre-trained Model and CNN-LSTM Approach
Hùng, B. T., Semwal, V. B., Gaud, N., & Bijalwan, V. (2021) · Algorithms for intelligent systems · doi:10.1007/978-981-33-6307-6_99 · Cited by 26
Link Prediction in Time Varying Social Networks
Carchiolo, V., Cavallo, C., Grassia, M., Malgeri, M., & Mangioni, G. (2022) · Information · doi:10.3390/info13030123 · Cited by 27
“…et al., in [8], report that, while deep learning has been successfully applied on a wide variety of tasks [9], from speech recognition [10,11] and machine translation [12] to image analysis and computer vision [13–15], there is now a growing interest in trying to learn on non-Euclidean data.”
BackgroundOnline Regularized Nonlinear AccelerationPreprint
Scieur, D., Oyallon, E., d’Aspremont, A., & Bach, F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09639 · Cited by 26
Deep Learning Assisted Automated Assessment of Thalassaemia from Haemoglobin Electrophoresis Images
Khan, M. S., Ullah, A., Khan, K. N., Riaz, H., Yousafzai, Y. M., Rahman, T., Chowdhury, M. E. H., & Kashem, S. B. A. (2022) · Diagnostics · doi:10.3390/diagnostics12102405 · Cited by 25
“Residual networks (in short ResNets), which have several variants, solve vanishing gradient and degradation problems [25] and learn from residuals instead of features [29].”
BackgroundArnaud, V., Pellegrino, F., Keenan, S., St-Gelais, X., Mathevon, N., Levréro, F., & Coupé, C. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010325 · Cited by 25
“NN have been around for several decades, but their performances have improved dramatically in the last decade after the discovery of how to efficiently train deeper architectures [80].”
Scene classification based on semantic labeling
Rangel, J. C., Cazorla, M., García-Varea, I., Martínez-Gómez, J., Fromont, É., & Sebban, M. (2016) · Advanced Robotics · doi:10.1080/01691864.2016.1164621 · Cited by 25
“The use of deep learning (DL) is considered as a remarkable milestone in the research areas of computer vision and robotics [10].”
BackgroundA pipelined and scalable dataflow implementation of convolutional neural networks on FPGA
Bacis, M., Natale, G., Sozzo, E. D., & Santambrogio, M. D. (2017) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2017.44 · Cited by 25
“Inspired by biological vision systems, Convolutional Neural Network (CNN) is a well-known deep learning algorithm extended from Artificial Neural Network (ANN) that has demonstrated significant success in various applications, such as image search engines in data centers, video surveillance and mobile robot vision [1,…”
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.