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 901–1,000 of 1,001
Reliability-Driven Memristive Crossbar Design in Neuromorphic Computing Systems
Xu, Q., Wang, J., Yuan, B., Sun, Q. L., Chen, S., Yu, B., Kang, Y., & Wu, F. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3125065 · Cited by 20
CoNNA – Compressed CNN Hardware Accelerator
STRUHARIK, R. J. R., Vukobratović, B. Z., Erdeljan, A., & Rakanovic, D. (2018) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd.2018.00070 · Cited by 20
“Keywords—machine learning, convolutional neural network, compressed CNN, hardware acceleration, FPGA I. INTRODUCTION Deep learning [1], and particularly Deep Neural Networks (DNNs), are currently one of the most intensively and widely used machine learning predictive models.”
BackgroundInfluentialSaini, M., & Susan, S. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9181-1_49 · Cited by 20
Deep multi-scale feature fusion for pancreas segmentation from CT images
Chen, Z., Wang, X., Yan, K., & Zheng, J. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02117-y · Cited by 20
“CNNs [7] have been proven to extract meaningful information from input data, which mainly consist of consecutive convolutional and pooling layers.”
BackgroundA deep learning approach to trespassing detection using video surveillance data
Bashir, M., Rundensteiner, E. A., & Ahsan, R. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006426 · Cited by 20
Automatic generation of software pipelines for heterogeneous parallel systems
Pienaar, J. A., Chakradhar, S., & Raghunathan, A. (2012) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/sc.2012.22 · Cited by 20
“applications [56] including handwriting recognition, automotive safety, video surveillance, and face detection [57].”
BackgroundMultiscale Hierarchical Convolutional NetworksPreprint
Jacobsen, J.-H., Oyallon, E., Mallat, S., & Smeulders, A. W. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.04140 · Cited by 21
“Deep convolutional networks transforms x into multiple layers x j of coefficients at depths j , whose dimensions are progressively reduced after a certain depth (LeCun et al., 2010).”
BackgroundClassification of Quantitative Light-Induced Fluorescence Images Using Convolutional Neural NetworkPreprint
Imangaliyev, S., van der Veen, M. H., Volgenant, C. M. C., Loos, B. G., Keijser, B. J. F., Crielaard, W., & Levin, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.09193 · Cited by 20
“ResNet and many other architectures [7,12] use convolutional operator in extracting useful feature mappings in image classification task.”
Bulletin of the Polish Academy of Sciences: Technical Sciences
Grochowski, M., Kwasigroch, A., & Mikołajczyk, A. (2019) · Bulletin of the Polish Academy of Sciences Technical Sciences · doi:10.24425/bpas.2019.128485 · Cited by 20
“Basic convolutional neural network [31]”
Deep Object Detection based Mitosis Analysis in Breast Cancer Histopathological ImagesPreprint
Sohail, A., Mukhtar, M. A., Khan, A., Zafar, M. M., Zameer, A., & Khan, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08803 · Cited by 20
“Moreover, a distinct characteristic of images is that preliminary features such as curves, semi-circles, circles, lines, edges, and color are shared among diverse categories of images [38].”
BackgroundEnhancing molecular property prediction with quantized GNN models
Rasool, A., Rahman, J. U., & Uwitije, R. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-00989-3 · Cited by 19
“Machine learning in chemistry utilizes a diverse toolkit, combining well-established models with advanced deep learning [4] techniques inspired by breakthroughs in computer vision (e.g., convolutional neural networks [5]) and natural language processing (e.g., sequence models [6]).”
Efficient Implementation of Max-Pooling Algorithm Exploiting History-Effect in Ferroelectric-FinFETs
Rafiq, M., Parihar, S. S., Chauhan, Y. S., & Sahay, S. (2022) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2022.3207114 · Cited by 19
“…convolutional neural networks (CNNs) which are extremely efficient for processing multidimensional data patterns such as images and videos have become the main stream technology for image recognition, image segmentation, natural language processing, speech recognition, etc. [2], [3], [4], [5].”
BackgroundFedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations
Wang, H., Chen, D., Kerkouche, R., & Fritz, M. (2024) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2024-0083 · Cited by 19
“We consider a standard classification task by training federated ConvNets (LeCun et al., 2010) on three benchmark datasets: MNIST (LeCun et al.”
MethodA Multimodal Learning-based Approach for Autonomous Landing of UAV
Neves, F. S. P., Branco, L. M., Pereira, M. I., Claro, R. M., & Pinto, A. M. (2024) · IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications · doi:10.1109/mesa61532.2024.10704866 · Cited by 19
“The progress made in this field over the past ten years has been specially fueled by the CNNs’ ongoing success in a variety of perception-related tasks [27].”
BackgroundProbing Equivariance and Symmetry Breaking in Convolutional Networks
Vadgama, S., Islam, M., Buracas, D., Shewmake, C., Moskalev, A., & Bekkers, E. J. (2025) · neural information processing systems · doi:10.52202/085713-4050 · Cited by 19
“Weight sharing in convolutional networks was introduced in [LeCun et al., 2010] for images, and extended to group transformation in [Cohen and Welling, 2016] (recently formalized for MPNNs [Bekkers et al., 2024]).”
Li, Y., & Shibuya, T. (2015) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2015.7359861 · Cited by 19
“For more details on the CNN, readers are referred to [23, 24, 25, 26, 27, 28].”
BackgroundRoad network extraction in high-resolution SAR images based CNN features
Li, Y., Zhang, R., & Wu, Y. (2017) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2017.8127293 · Cited by 19
Hyperdrive: A Multi-Chip Systolically Scalable Binary-Weight CNN Inference Engine
Andri, R., Cavigelli, L., Rossi, D., & Benini, L. (2019) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2019.2905654 · Cited by 19
“What used to be image recognition on small images [3, 4] has evolved to object segmentation and detection [5–9] in highresolution frames—and the next step, video analysis, is already starting to gain traction [10–12].”
BackgroundApplication of Computer Vision and Deep Learning in Breast Cancer Assisted Diagnosis
Gu, Y., & Jiayao, Y. (2019) · International Conference on Machine Learning and Soft Computing (ICMLSC) · doi:10.1145/3310986.3311010 · Cited by 19
“It is the best image recognition machine learning algorithm [14].”
BackgroundHierarchical Comprehensive Context Modeling for Chinese Text Classification
Jin-gang, L., Xia, C., Yan, H., Xie, Z., & Sun, J. (2019) · IEEE Access · doi:10.1109/access.2019.2949175 · Cited by 19
“The basic structure of traditional CNNs usually includes components such as a convolutional layer [4], an activation function [26], a pooling layer [27], and an output layer.”
BackgroundEvaluating Performance, Power and Energy of Deep Neural Networks on CPUs and GPUs
Sun, Y., Ou, Z., Chen, J., Qi, X., Guo, Y., Cai, S., & Yan, X. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-7443-3_12 · Cited by 19
Enhanced Spatial Attention Graph for Motion Planning in Crowded, Partially Observable Environments
Shi, W., Zhou, Y., Zeng, X., Li, S., & Bennewitz, M. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812322 · Cited by 19
“However, they need to fix the size of the input or convert spatial relations as an occupancy grid map, and then use CNNs [22] and pooling.”
A three-dimensional prediction method of stiffness properties of composites based on deep learning
Su, H., Guan, T., & Liu, Y. (2022) · Computational Mechanics · doi:10.1007/s00466-022-02253-z · Cited by 19
“The CNN extracts image features from the original data and establishes the mapping from image features to desired results of the task [22,23].”
MethodA Review of Techniques on Gait-Based Person Re-Identification
Rahi, B. H., Li, M., & Qi, M. (2023) · International Journal of Network Dynamics and Intelligence · doi:10.53941/ijndi0201005 · Cited by 19
Convolutional Nonlinear Neighbourhood Components Analysis for Time Series Classification
Zheng, Y., Liu, Q., Chen, E., Zhao, J. L., He, L., & Lv, G. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-18032-8_42 · Cited by 19
“For the traditional CNN, it could consist of multiple stages and each stage contains three cascaded layers [8,9,11,21,24].”
MethodDeep‐learning‐based scenario generation strategy considering correlation between multiple wind farms
Xu, Y., Shi, L., & Ni, Y. (2017) · The Journal of Engineering · doi:10.1049/joe.2017.0722 · Cited by 19
Manko, S., Diane, S., Krivoshatskiy, A. E., Margolin, I. D., & Slepynina, E. A. (2018) · IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering · doi:10.1109/eiconrus.2018.8317240 · Cited by 19
“The 1st type is the motion of each robotic agent in its own separate trajectory, following the route generated with A* algorithm [12].”
MethodThe Stochastic Complexity of Spin Models: Are Pairwise Models Really Simple?
Beretta, A., Battistin, C., de Mulatier, C., Mastromatteo, I., & Marsili, M. (2018) · Entropy · doi:10.3390/e20100739 · Cited by 19
“A statistical model trained on a sufficiently large number of instances can learn how to mimic the performance of the human brain on these tasks [4,5].”
Accelerating High-Resolution Seismic Imaging by Using Deep Learning
Liu, W., Cheng, Q., Liu, L., Wang, Y., & Zhang, J. (2020) · Applied Sciences · doi:10.3390/app10072502 · Cited by 19
“Both the learned network and the QPSTM exhibit a comparable performance in terms of the frequency improvement. of each patch by the trained CNN requires approximately 10 ms when using one TITAN Xp GPU, which means that computing the profile (1001 (vertical) × 601 (inline) samples) shown in Figure 14 requires only 3 s.”
MethodLow Cost Defect Detection Using a Deep Convolutional Neural Network
Tulbure, A. A., & Dulf, E. H. (2020) · IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR) · doi:10.1109/aqtr49680.2020.9130004 · Cited by 19
“A path for further improvements is to modify the architecture in a residual network architecture as the architecture has the biggest weight in modifying the results [5] [10].”
BackgroundDistributed Sequence Memory of Multidimensional Inputs in Recurrent NetworksPreprint
Charles, A. S., Yin, D., & Rozell, C. J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08346 · Cited by 20
“In fact, some classes of deep neural networks have been designed to induce sparsity at higher layers that may serve as inputs into the recurrent layers (LeCun et al., 2010; Kavukcuoglu et al., 2010).”
BackgroundSparse Concept Bottleneck Models: Gumbel Tricks in Contrastive LearningPreprint
Semenov, A., Ivanov, V., Beznosikov, A. N., & Gasnikov, A. V. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.03323 · Cited by 19
“Early works of (Koh et al., 2020; Losch et al., 2019; Marcos et al., 2020) proposes to train CNN (LeCun et al., 2010) and create an additional layer before the last fully connected layer where each neuron corresponds to a human interpretable concept.”
BackgroundUnCNN: A New Directed CNN Model for Isolated Arabic Handwritten Characters Recognition
Khayati, M. E., & Elkettani, Y. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-06652-5 · Cited by 18
“Depending on the number of filters (depth), the CL outputs a set of filtered images called feature maps [66].”
BackgroundDetection of Cavities from Oral Images using Convolutional Neural Networks
Khan, M. A. H., Giri, P. S., & Jothi, J. A. A. (2022) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet55527.2022.9872786 · Cited by 18
“The proposed Dental-Net was trained for 25 epochs, with Adam’s propagation and binary cross entropy as the empirical loss function [18].”
BackgroundMethodEffective Deep Learning Seasonal Prediction Model for Summer Drought Over China
Liu, W., Huang, Y., & Wang, H. (2024) · Earth s Future · doi:10.1029/2023ef004409 · Cited by 18
“Convolutional neural networks (CNN) have developed rapidly (Bouv-rie, 2006; Fukushima, 1975, 2013; LeCun et al., 1989, 2010) and their superiority in atmospheric science has been continuously demonstrated.”
BackgroundMulti‐label logo recognition and retrieval based on weighted fusion of neural features
Bernabeu, M., Gallego, A., & Pertusa, A. (2024) · Expert Systems · doi:10.1111/exsy.13627 · Cited by 18
“Specific proposals for this dataset were also considered, such as the work of Tursun et al. [27], in which six hand-crafted features are combined with NCs extracted from three different CNN architectures.”
InfluentialStatistical localization exploiting convolutional neural network for an autonomous vehicle
Ishibushi, S., Taniguchi, A., Takano, T., Hagiwara, Y., & Taniguchi, T. (2015) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon.2015.7392291 · Cited by 18
Manjusha, K., Kumar, M. A., & Soman, K. P. (2018) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-018-0308-z · Cited by 18
Vibration signal based condition monitoring of mechanical equipment with scattering transform
Ambika, P. S., Rajendrakumar, P. K., & Ramchand, R. (2019) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-019-0604-7 · Cited by 18
Tumour Detection using Convolutional Neural Network on a Lightweight Multi-Core Device
Teo, T. H., Tan, W. M., & Tan, Y. S. (2019) · IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) · doi:10.1109/mcsoc.2019.00020 · Cited by 18
“Traditionally, the nonlinearity layer consists of tanh() sigmoid function or the logistic sigmoid function, as described in [10].”
BackgroundMethodInfluentialSun, J., & Frishman, D. (2020) · Journal of Structural Biology · doi:10.1016/j.jsb.2020.107574 · Cited by 18
Tectonic discrimination and application based on convolution neural network and incomplete big data
Ge, C., Huo, J., Gu, H., Wang, F., Sun, H., Li, X., Li, W., & Feng, Y. (2020) · Journal of Geochemical Exploration · doi:10.1016/j.gexplo.2020.106662 · Cited by 18
Autonomous CNN (AutoCNN): A data-driven approach to network architecture determination
Aradhya, A. M. S., Ashfahani, A., Angelina, F., Pratama, M., de Mello, R. D., & Sundaram, S. (2022) · Information Sciences · doi:10.1016/j.ins.2022.05.100 · Cited by 15
Ajala, S., Jalajamony, H. M., Nair, M., Marimuthu, P., & Fernandez, R. E. (2022) · Scientific Reports · doi:10.1038/s41598-022-16114-5 · Cited by 18
“CNNs have at least one layer that uses the convolution operation to extract features 57,58 .”
BackgroundDeep learning applied to analyze patterns from evaporated droplets of Viscum album extracts
Acuña, C., y Terán, A. M., Kokornaczyk, M. O., Baumgartner, S., & Castelán, M. (2022) · Scientific Reports · doi:10.1038/s41598-022-19217-1 · Cited by 18
Assefa, A. A., Tian, W., Acheampong, K. N., Aftab, M. U., & Ahmad, M. I. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/9325803 · Cited by 18
“Insufficient feature strength in small objects and the stochastic nature of kernel initialization are the leading cause of incapability in detecting small objects [2, 3].”
BackgroundLatent Semantic Representation Learning for Scene Classification
Li, X. S., & Guo, Y. (2014) · International Conference on Machine Learning · Cited by 18
Wu, Y., Zhang, R., & Zhan, Y. (2018) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2018.8518463 · Cited by 18
Du, Y., Bourlai, T., & Dawson, J. M. (2016) · IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS) · doi:10.1109/btas.2016.7791162 · Cited by 18
“posed of three layers: a convolution layer, a non-linearity layer, and a feature pooling layer [11].”
BackgroundDelay Compensated Asynchronous Adam Algorithm for Deep Neural Networks
Guan, N., Shan, L., Yang, C., Xu, W., & Zhang, M. (2017) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa/iucc.2017.00130 · Cited by 18
“The DNN models, such as convolutional neural networks (CNN, [2]), have achieved great successes in many applications such as computer vision [4] [5], speech recognition [6], and natural language processing [7] [8].”
MethodMicroarray camera image segmentation with Faster-RCNN
Zou, J., & Song, R. (2018) · 2018 IEEE International Conference on Applied System Invention (ICASI) · doi:10.1109/icasi.2018.8394403 · Cited by 18
“In recent years, deep convolution neural networks have been successfully applied to object detection and image segmentation [1][2].”
MethodQuantification of MagLIF morphology using the Mallat scattering transformation
Glinsky, M. E., Moore, T. W., Lewis, W. E., Weis, M. R., Jennings, C. A., Ampleford, D. J., Knapp, P. F., Harding, E. C., Gomez, M. R., & Harvey-Thompson, A. J. (2020) · Physics of Plasmas · doi:10.1063/5.0010781 · Cited by 18
ML-Misfit: Learning a Robust Misfit Function for Full-Waveform Inversion Using Machine Learning
Sun, B., & Alkhalifah, T. A. (2020) · EAGE Annual Conference & Exhibition · doi:10.3997/2214-4609.202010466 · Cited by 18
An Analysis of the Connections Between Layers of Deep Neural NetworksPreprint
Culurciello, E., Jin, J., Dündar, A., & Bates, J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.0152 · Cited by 18
“Using the naming convention in [8], for each layer l, xi is an input feature map, yi is an output feature map.”
BackgroundMethodDeep Learning by ScatteringPreprint
Mallat, S., & Waldspurger, I. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.5532 · Cited by 18
“Most deep neural networks cascade linear operators followed by “pooling non-linearities” which aggregatemultiple variables [9, 5, 6, 7, 11].”
BackgroundInterneuron diversity and normalization specificity in a visual systemPreprint
Seung, H. S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.04.03.587837 · Cited by 18
“Spatial and feature normalization can be combined by pooling over multiple locations in multiple feature maps (LeCun, Kavukcuoglu, and Farabet 2010; Wu and He 2018).”
BackgroundMethodSurface Defect Detection of Fabric Based on Improved Faster R-CNN
Hou, W., Wen, S., Li, P., & Feng, S. (2023) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece58870.2023.10263522 · Cited by 17
Ensemble Deep Learning for Wear Particle Image Analysis
Shah, R., Sridharan, N. V., Mahanta, T. K., Amarnath, M., Sugumaran, V., Ramteke, S. M., & Marian, M. (2023) · Lubricants · doi:10.3390/lubricants11110461 · Cited by 17
Ünlü, A., Ulusoy, E., Yiğit, M. G., Darcan, M., & Doğan, T. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103017 · Cited by 17
A Real-Time Framework for EEG Signal Decoding With Graph Neural Networks and Reinforcement Learning
Aung, H. W., Li, J. J., An, Y., & Su, S. W. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3558171 · Cited by 18
“Convolutional neural networks (CNNs), which mimic natural image recognition in the human visual system, are part of the deep learning family and excel in computer vision tasks [13], [14], [15].”
Dynamic Mode Decomposition-based surrogate modeling of wall shear stress in an aneurysm artery
Djuansjah, J., Omar, I., Alizadeh, A., Sadeq, A. M., Hussein, S. A., Singh, N. S. S., Rajab, H., & Hajlaoui, K. (2025) · Physics of Fluids · doi:10.1063/5.0284372 · Cited by 17
Automatic generation of software pipelines for heterogeneous parallel systems
Pienaar, J. A., Chakradhar, S., & Raghunathan, A. (2012) · IEEE International Conference on High Performance Computing, Data, and Analytics · doi:10.5555/2388996.2389029 · Cited by 17
Performance Evaluation of Neuromorphic-Vision Object Recognition Algorithms
Kasturi, R., Goldgof, D. B., Ekambaram, R., Pratt, G. A., Krotkov, E., Hackett, D. D., Yang, R., Zheng, Q., Sharma, R., Anderson, M. B., et al. (2014) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2014.416 · Cited by 16
“The classification step uses a feedforward multi-layered convolutional neural net [4] approach that is fast, efficient and inherently parallel.”
MethodEfficient Data Encoding for Convolutional Neural Network application
Trinh, H.-P., Duranton, M., & Paindavoine, M. (2015) · ACM Transactions on Architecture and Code Optimization · doi:10.1145/2685394 · Cited by 17
“Becuase S 1 always indicates the sign of number (cf. Section is inactive), then if S P 1 S Q 1 0 : A B , if S P 1 with second positions and so on. positions together: S P S”
BackgroundConvolutional Neural Network implementation for image-based Salak sortation
Rismiyati, & Azhari, S. N. (2016) · International Conference on Science and Technology (ICST) · doi:10.1109/icstc.2016.7877351 · Cited by 17
“CONVOLUTIONAL NEURAL NETWORK Convolutional Neural Network (CNN) is one of deep learning methods that is used for processing data with gridlike topology.”
BackgroundInfluentialReal-Time Biologically Inspired Action Recognition from Key Poses Using a Neuromorphic Architecture
Layher, G., Brosch, T., & Neumann, H. (2017) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2017.00013 · Cited by 17
“A deep convolutional neural network is typically organized in a feedforward cascade of layers composed of artificial neurons (LeCun et al., 2010), which process the output of the proceeding layer (afferent synaptic connections) and propagate the result to the subsequent one (efferent synaptic…”
BackgroundSteganalysis using learned denoising kernels
Singh, B., Chhajed, M., Sur, A., & Mitra, P. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09960-w · Cited by 17
“1 A hypothetical model for a typical CNN [18].”
BackgroundKarthiga, R., & Narasimhan, K. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1767/1/012042 · Cited by 17
“Fabio et al. introduced a breast cancer dataset for histopathology images (BreakHis), acquired from 82 patients [26].”
BackgroundConvolutional Neural Network Based Advertisement Classification Models for Online English Newspapers
Jain, P. (2021) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.17762/turcomat.v12i2.1505 · Cited by 17
“CNN (LeCun et al., 2010; Krizhevsky et al., 2017; Shaheen & Verma, 2016) is a deep learning architecture that contains many hidden layers including convolutional layer, pooling layers, fully connected layers and flatten layers.”
BackgroundClassification of Pandavas Figure in Shadow Puppet Images using Convolutional Neural Networks
Supriyanti, W., & Anggoro, D. A. (2021) · Khazanah Informatika Jurnal Ilmu Komputer dan Informatika · doi:10.23917/khif.v7i1.12484 · Cited by 17
“[10] Y. LeCun, K. Kavukcuoglu, and C. Farabet, “Convolutional networks and applications in vision,” in ISCAS 2010 - 2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems, 2010, pp. 253–256.”
MethodInfluentialA topic-based multi-channel attention model under hybrid mode for image caption
Qian, K., & Tian, L. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06557-8 · Cited by 17
“…unit (CPU), graphics processing unit (GPU) hardware resources, as well as the development of convolutional neural network (CNN) [14, 15] and recurrent neural networks (RNNs) [16–19] and the emergence of image annotation data sets, image caption-related technologies have developed rapidly.”
BackgroundAltıntop, Ç. G., Latifoğlu, F., Akın, A. K., & Çetin, B. (2021) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2021.11.003 · Cited by 18
Deep Features Comparative Analysis for COVID-19 Detection from the Chest Radiograph Images
Ullah, N., & Javed, A. (2021) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit53504.2021.00055 · Cited by 17
Material measurement units for a circular economy: Foundations through a review
Zocco, F., McLoone, S., & Smyth, B. M. (2022) · Sustainable Production and Consumption · doi:10.1016/j.spc.2022.05.022 · Cited by 17
“The most used computer vision methods belonging to this second category are based on convolutional neural networks (CNNs) [34, 18].”
MethodNandyal, S., & Kattimani, S. L. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130644 · Cited by 17
“CNNs (Convolutional Neural Networks) [11, 12] are a deep learning architecture that is being used to classify images [13].”
BackgroundEncrypted Network Traffic Classification with Higher Order Graph Neural Network
Okonkwo, Z., Foo, E., Hóu, Z., Li, Q., & Jadidi, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35486-1_27 · Cited by 17
Yahyatabar, M., & Ghasemi, J. (2017) · IET Biometrics · doi:10.1049/iet-bmt.2016.0103 · Cited by 17
“The elementary visual characteristics such as edges, end points and corners are extracted by using local receptive fields [21].”
MethodFani, M., Yazdi, M., Clausi, D. A., & Wong, A. K. C. (2017) · IEEE Access · doi:10.1109/access.2017.2769140 · Cited by 17
Neural network approach for multispectral image processing
Podorozhniak, A., Liubchenko, N., Balenko, O., & Жуйков, Д. (2018) · IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET) · doi:10.1109/tcset.2018.8336357 · Cited by 17
SAR Image Simulation by Generative Adversarial Networks
Bao, X., Pan, Z., Liu, L., & Lei, B. (2019) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2019.8899286 · Cited by 17
“Over recent years, the landscape of computer vision has been drastically altered and pushed forward through an efficient, end-to-end learning framework, the Convolutional Neural Networks [4].”
BackgroundSatellite Image Classification and Segmentation with Transfer Learning
do Nascimento, R. G., & Viana, F. A. C. (2020) · AIAA SciTech Forum · doi:10.2514/6.2020-1864 · Cited by 17
“Introduction D convolutional neural networks [6] have shown success in image classification [3, 7, 8] object detection, image segmentation [4, 9], and many other recognition problems in computer vision.”
BackgroundDeng, Z., Cao, Y., Zhou, X., Yi, Y., Jiang, Y., & You, I. (2020) · Sensors · doi:10.3390/s20102866 · Cited by 17
“Colors are the basic elements in vision problems, as they can be treated as detailed data contributing to greater performance of image recognition [30], object detection [31], etc.”
BackgroundOn the Limits of Parallelizing Convolutional Neural Networks on GPUs
Pourghassemi, B., Zhang, C., Lee, J. H., & Chandramowlishwaran, A. M. (2020) · ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) · doi:10.1145/3350755.3400266 · Cited by 17
“with several applications such as computer vision [12, 17], voice recognition [2], recommender systems [23], physics simulations [15], and natural language processing [6, 9].”
BackgroundPlebe, A., & Lio, M. D. (2020) · IEEE Access · doi:10.1109/access.2020.3028185 · Cited by 18
Recognizing Very Small Face Images Using Convolution Neural Networks
Horng, S., Supardi, J., Zhou, W., Lin, C., & Jiang, B. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3032396 · Cited by 17
Fast signal quality monitoring for coherent communications enabled by CNN-based EVM estimation
Fan, Y., Udaļcovs, A., Pang, X., Natalino, C., Furdek, M., Popov, S., & Ozoliņš, O. (2020) · Journal of Optical Communications and Networking · doi:10.1364/jocn.409704 · Cited by 17
Pakistani traffic-sign recognition using transfer learning
Nadeem, Z., Khan, Z., Mir, U., Mir, U. I., Khan, S., Nadeem, H., & Sultan, J. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12177-8 · Cited by 17
“13, 14, 15, and 16 considering the German (or GTSRB) and the Pakistani (or PTSD) datasets, respectively.”
BackgroundComputational approaches in electrical impedance tomography with applications to head imaging
Candiani, V. (2021) · Aaltodoc (Aalto University) · Cited by 17
Algorithmic Behavioral Science: Machine Learning as a Tool for Scientific DiscoveryPreprint
Ludwig, J., & Mullainathan, S. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4164272 · Cited by 17
Bat Optimization Assisted Diabetic Retinopathy Detection Framework
AlBalushi, F. M. (2020) · Multimedia Research · doi:10.46253/j.mr.v3i2.a3 · Cited by 16
“It makes a diagnosis of DR by mining the optic disc by focusing on the above-said issues in the existing systems [15].”
BackgroundGenerating Paired Seismic Training Data with Cycle-Consistent Adversarial Networks
Zhang, Z., Yan, Z., Jing, J., Gu, H., & Li, H. (2023) · Remote Sensing · doi:10.3390/rs15010265 · Cited by 16
Huang, Z. A., Sang, Y., Sun, Y., & Lv, J. (2023) · Neural Computing and Applications · doi:10.1007/s00521-022-08135-y · Cited by 16
Large-Scale LoD2 Building Modeling using Deep Multimodal Feature Fusion
Vostikolaei, F. S., & Jabari, S. (2023) · Canadian Journal of Remote Sensing · doi:10.1080/07038992.2023.2236243 · Cited by 16
“With the rapid development of big data and high-performance computers, deep learning, especially Convolutional Neural Networks (CNNs), can help with classification tasks, e.g., image classification, segmentation, and scene understanding (LeCun et al. 2010).”
BackgroundA sleep staging model on wavelet-based adaptive spectrogram reconstruction and light weight CNN
Fei, K., Wang, J., Pan, L., Wang, X., & Chen, B. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108300 · Cited by 16
Semi-Supervised Speckle Noise Reduction in OCT Images With UNet and Swin-Uformer
Chen, Y., Li, J., Luo, Z., Fei, K., Luo, Y., Duan, Z., Yuan, J., & Xiao, P. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3381655 · Cited by 16
“CNNs are biologically inspired trainable architectures composed of multiple stages [38].”
BackgroundSayed, M. (2024) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2024.p0668 · Cited by 16
Down to earth! Guidelines for DGA-based Malware Detection
Cebere, B. C., Flueren, J. L. B., Sebastián, S., Plohmann, D., & Rossow, C. (2024) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1145/3678890.3678913 · Cited by 17
“A1: AGDs’ structural patterns differ from non-DGA samples, regardless of the generator family.”
Understanding Polymers Through Transfer Learning and Explainable AI
Miccio, L. A. (2024) · Applied Sciences · doi:10.3390/app142210413 · Cited by 16
Moqadam, H., & Eisen, O. (2025) · The Cryosphere · doi:10.5194/tc-19-2159-2025 · Cited by 16
Wiebe, N., Kapoor, A., & Svore, K. M. (2014) · arXiv · doi:10.48550/arxiv.1412.3489 · Cited by 5
“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].”
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.