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 201–300 of 1,001
Estimation of daily global solar radiation using deep learning model
Kaba, K., Sarıgül, M., Avcı, M., & Kandırmaz, H. M. (2018) · Energy · doi:10.1016/j.energy.2018.07.202 · Cited by 161
LETRIST: Locally Encoded Transform Feature Histogram for Rotation-Invariant Texture Classification
Song, T., Li, H., Meng, F., Wu, Q., & Cai, J. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2671899 · Cited by 161
“deep convolutional neural networks (CNNs) [29] alternates”
Music Mood Detection Based On Audio And Lyrics With Deep Neural NetPreprint
Delbouys, R., Hennequin, R., Piccoli, F., Royo-Letelier, J., & Moussallam, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.07276 · Cited by 160
“division of audio and lyrics requires synchronization of the modalities. 3.1 Audio only We use a mel-spectrogram as input, which are 2- dimensional. We choose a convolutional neural network (ConvNet) [17], the architecture is shown in Fig. 1 (a). It is composed of two consecutive 1-dimensional convolution layers (conv…”
MethodInfluentialActive Self-Paced Learning for Cost-Effective and Progressive Face Identification
Lin, L., Wang, K., Meng, D., Zuo, W., & Zhang, L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2652459 · Cited by 159
“We thus utilize the deep convolutional neural network (CNN) [20], [21] for feature extraction instead of using handcraft image features.”
MethodDeep learning similarities from different representations of source code
Tufano, M., Watson, C., Bavota, G., Di Penta, M., White, M., & Poshyvanyk, D. (2018) · Proceedings of the 15th International Conference on Mining Software Repositories · doi:10.1145/3196398.3196431 · Cited by 158
“fields [43, 48].”
A Privacy-Preserving and Verifiable Federated Learning Scheme
Zhang, X., Fu, A., Wang, H., Zhou, C., & Chen, Z. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9148628 · Cited by 158
“Nowadays, deep learning has been applied extensively in computer vision [1], speech recognition [2], disease diagnosis [3] and etc. Companies such as Google and Apple use massive amounts of data collected from multiple users to train models, and the resulting model has unprecedented accuracy.”
BackgroundHiding Data in Images Using Cryptography and Deep Neural Network
Sharma, K., Aggarwal, A., Singhania, T., Gupta, D., & Khanna, A. (2019) · Journal of Artificial Intelligence and Systems · doi:10.33969/ais.2019.11009 · Cited by 160
“Since the structure and the weights can be randomized, the network will hide the data that cannot be known to anybody who doesn't have the weights [29], [30].”
BackgroundMaheswari, P., Raja, P., Apolo-Apolo, O. E., & Ruiz, M. P. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.684328 · Cited by 158
Applications of Deep Learning in Intelligent Transportation Systems
Haghighat, A. K., Mouli, V. R., Chakraborty, P., Esfandiari, Y., Arabi, S., & Sharma, A. (2020) · Journal of Big Data Analytics in Transportation · doi:10.1007/s42421-020-00020-1 · Cited by 155
“Adversarial attacks are therefore an increasing area of focus in di ff erent DL application research topics such as natural language processing, computer vision, speech recognition and malware detection [249, 250, 251, 252, 253].”
BackgroundDeep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
Kwasigroch, A., Jarzembiński, B., & Grochowski, M. (2018) · International Interdisciplinary PhD Workshop (IIPhDW) · doi:10.1109/iiphdw.2018.8388337 · Cited by 152
“Basic deep convolutional network architecture [18]”
Rethinking Automatic Chord Recognition with Convolutional Neural Networks
Humphrey, E. J., & Bello, J. P. (2012) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2012.220 · Cited by 152
“Another preliminary processing stage, popularized in computer vision, is the application of subtractive-divisive contrast normalization [5], which serves as a frequencyvarying gain control.”
BackgroundMethodMonte Carlo DropBlock for modeling uncertainty in object detection
Yelleni, S. H., Kumari, D., Srijith, P. K., & Mohan, C. K. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110003 · Cited by 152
Kolmogorov-Arnold Convolutions: Design Principles and Empirical StudiesPreprint
Сергеевич, Д. И. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.01092 · Cited by 153
“Convolutional Neural Networks (CNNs), initially proposed by LeCun et al. [1], have become a cornerstone in this domain due to their ability to efficiently process high-dimensional data arrays such as images.”
BackgroundAn Interactive Node-Link Visualization of Convolutional Neural Networks
Harley, A. W. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-27857-5_77 · Cited by 150
“The most common simplified representation replaces each layer of nodes with a solid block, and replaces the dense connections between layers with either a single arrow pointing from one layer to the next [1], or with edges connecting the outskirts of the layers [13].”
BackgroundCancer neoantigen prioritization through sensitive and reliable proteogenomics analysis
Wen, B., Li, K., Zhang, Y., & Zhang, B. (2020) · Nature Communications · doi:10.1038/s41467-020-15456-w · Cited by 138
Machine Learning Refined: Foundations, Algorithms, and Applications
Watt, J. M., Borhani, R., & Katsaggelos, A. K. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108690935 · Cited by 151
From handcrafted to learned representations for human action recognition: A survey
Zhu, F., Shao, L., Xie, J., & Fang, Y. (2016) · Image and Vision Computing · doi:10.1016/j.imavis.2016.06.007 · Cited by 148
Kainz, P., Pfeiffer, M., & Urschler, M. (2017) · PeerJ · doi:10.7717/peerj.3874 · Cited by 149
“Recently, deep learning methods, especially convolutional neural networks (CNNs) ( LeCun, Kavukcuoglu & Farabet, 2010 ), have received substantial attention in the medical imaging domain.”
A Short-Term Rainfall Prediction Model Using Multi-task Convolutional Neural Networks
Qiu, M., Zhao, P., Zhang, K., Huang, J., Shi, X., Wang, X., & Chu, W. (2017) · 2017 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2017.49 · Cited by 128
“Convolutional neural networks have been widely used in images, speech, and time series tasks [3], [5], [6] as CNNs are able to extract deep features from the raw data.”
BackgroundSteering a predator robot using a mixed frame/event-driven convolutional neural network
Moeys, D. P., Corradi, F., Kerr, E., Vance, P., Das, G., Neil, D., Kerr, D., & Delbruck, T. (2016) · 2016 Second International Conference on Event-based Control, Communication, and Signal Processing (EBCCSP) · doi:10.1109/ebccsp.2016.7605233 · Cited by 122
Hwang, B., You, J., Vaessen, T., Myin‐Germeys, I., Park, C., & Zhang, B. (2018) · Telemedicine Journal and e-Health · doi:10.1089/tmj.2017.0250 · Cited by 147
“The main purpose of this study is to extract hidden feature representations using 1D CNNs by training the whole process from raw signal input to class label outputs in the manner of seamless end-to-end learning.(8,9,13) CNNs, one of the popular deep learning models, were used as a basic unit in the whole learning arch…”
Yu, Z., Niu, Z., Tang, W., & Wu, Q. (2019) · IEEE Access · doi:10.1109/access.2019.2895604 · Cited by 147
“On the basis of DBN, Stacked Auto-Encoders (SAE) [18], Convolutional Neural Network (CNN) [19] and Recurrent Neural Networks (RNN) [20] were developed.”
MethodTree LSTMs with Convolution Units to Predict Stance and Rumor Veracity in Social Media Conversations
Kumar, S., & Carley, K. M. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1498 · Cited by 145
“Convolution neural networks (LeCun et al., 2010) are popular in computer vision tasks for quite some time but lately they have shown potential in NLP tasks as well (Zhang et al.”
BackgroundKalra, S., Tizhoosh, H. R., Shah, S., Choi, C., Damaskinos, S., Safarpoor, A., Shafiei, S., Babaie, M., Diamandis, P., Campbell, C. J. V., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0238-2 · Cited by 132
Radar HRRP Target Recognition Model Based on a Stacked CNN–Bi-RNN With Attention Mechanism
Pan, M., Liu, A., Yu, Y., Wang, P., Li, J., Liu, Y., Lv, S., & Zhu, H. L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3055061 · Cited by 145
“A. CNN [30]–[35], [45] The CNN uses the local correlation of adjacent range cells in the HRRPs, and the HRRPs are hierarchically abstracted through the convolutional layer to obtain its high-level feature representation gradually.”
MethodSurvey of Deep Learning Paradigms for Speech Processing
Bhangale, K. B., & Kothandaraman, M. (2022) · Wireless Personal Communications · doi:10.1007/s11277-022-09640-y · Cited by 145
“[29] presented semi-supervised learning, which collaborates supervised deep learning for labeled data and unsupervised learning for un-labeled data to achieve meaningful representation of the features.”
BackgroundConvolutional Neural Network for Multi-Category Rapid Serial Visual Presentation BCI
Manor, R., & Geva, A. B. (2015) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2015.00146 · Cited by 144
“These networks have shown to be able to handle large variability in the data, which make them appealing for use with EEG. Specifically, convolutional neural networks (CNNs or ConvNets; LeCun et al., 2010 appear to be a good fit for EEG data (Cecotti and Gräser, 2011).”
BackgroundViolence Detection in Video by Using 3D Convolutional Neural Networks
Ding, C., Fan, S., Zhu, M. F., Feng, W., & Jia, B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-14364-4_53 · Cited by 144
Identification of Cotton Leaf Lesions Using Deep Learning Techniques
Caldeira, R. F., Santiago, W. E., & Teruel, B. (2021) · Sensors · doi:10.3390/s21093169 · Cited by 145
“A more detailed description of this kind of model can be found in Lecun et al. [43].”
MethodMultimodal Sarcasm Detection via Hybrid Classifier with Optimistic Logic
Bavkar, D. M., Kashyap, R., & Khairnar, V. D. (2022) · Journal of Telecommunications and Information Technology · doi:10.26636/jtit.2022.161622 · Cited by 143
“Metrics Methods HC+ PRO [50] HC+ AO [43] HC+ SSO [51] HC+ CMBO [52] HC+ ALO [53] CNN [54] RNN [55] RF [56] NB [54] BiGRU [26] NN [23] HC+ OLAO”
Deep Supervised and Contractive Neural Network for SAR Image Classification
Geng, J., Wang, H., Fan, J., & Ma, X. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2645226 · Cited by 142
“Typical DNN models include deep belief networks (DBNs) [21], deep Boltzmann machines [22], convolutional NNs [23], [24], and stacked autoencoders (SAEs) [25].”
BackgroundKidney segmentation from computed tomography images using deep neural network
da Cruz, L. B., Araújo, J. D. L., Ferreira, J. L., Diniz, J. O. B., Silva, A. C., de Almeida, J. D. S., de Paiva, A. C., & Gattass, M. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103906 · Cited by 142
Canonical correlation analysis networks for two-view image recognition
Yang, X., Liu, W., Tao, D., & Cheng, J. S. (2017) · Information Sciences · doi:10.1016/j.ins.2017.01.011 · Cited by 138
Land-Use Classification via Extreme Learning Classifier Based on Deep Convolutional Features
Weng, Q., Mao, Z., Lin, J., & Guo, W. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2672643 · Cited by 140
“DNN model, can learn robust and more discriminative features [9].”
MethodA survey on deep geometry learning: From a representation perspective
Xiao, Y., Lai, Y., Zhang, F., Li, C., & Gao, L. (2020) · Computational Visual Media · doi:10.1007/s41095-020-0174-8 · Cited by 139
“milar with pixels in 2D, the voxel-based representation also has a regular structure in the 3D space. The architectures of some neural networks which have been demonstrated useful in the 2D image eld [48, 50] can be easily extended to the voxel form. Nevertheless, adding one dimension means an exponentially increased…”
Allahham, M. S., Khattab, T. M., & Mohamed, A. M. S. (2020) · IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT) · doi:10.1109/iciot48696.2020.9089657 · Cited by 137
“The input and output of each layer are called feature maps [22].”
BackgroundCMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices
Capotondi, A., Rusci, M., Fariselli, M., & Benini, L. (2020) · IEEE Transactions on Circuits and Systems II: Express Briefs · doi:10.1109/tcsii.2020.2983648 · Cited by 135
“Concerning the deployment of deep inference networks, several works introduced frameworks, software stacks, and hardware solutions optimized in terms of latency and energy consumption [2], [15]–[19].”
Hyperspectral Image Classification Based on Three-Dimensional Scattering Wavelet Transform
Tang, Y. Y., Lu, Y., & Yuan, H. (2014) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2360672 · Cited by 135
“operators, like in convolution network architectures [34], [35]”
BackgroundLi, X., La, R., Wang, Y., Hu, B., & Zhang, X. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00192 · Cited by 115
“In simulating orientation-selective simple cells in the primary visual cortex of the brain (LeCun et al., 2010), convolution is considered to be an indispensable component of CNN frameworks.”
BackgroundMethodHow machine learning is shaping cognitive neuroimaging
Varoquaux, G., & Thirion, B. (2014) · GigaScience · doi:10.1186/2047-217x-3-28 · Cited by 110
“David Marr’s seminal work [15] formalized the idea of hierarchical levels of representation that tie together the receptive fields observed in visual cortex, but is also reflected in modern state-of-the-art computer vision architecture based on convolutional networks [16].”
BackgroundHealthcare Techniques Through Deep Learning: Issues, Challenges and Opportunities
Nisar, D.-E.-M., Amin, R., Shah, N.-U.-H., Ghamdi, M. A. A., Almotiri, S. H., & Alruily, M. (2021) · IEEE Access · doi:10.1109/access.2021.3095312 · Cited by 135
“, the Convolution layer and the pooling layer [103].”
BackgroundGeng, Z., Zhang, Y., Li, C., Han, Y. M., Cui, Y., & Yu, B. (2019) · Energy · doi:10.1016/j.energy.2019.116851 · Cited by 131
Metaheuristic Algorithms for Convolution Neural Network
Rere, L. M. R., Fanany, M. I., & Arymurthy, A. M. (2016) · Computational Intelligence and Neuroscience · doi:10.1155/2016/1537325 · Cited by 132
“performance on a number of tasks for pattern recognition using error gradient method [21].”
BackgroundMethodWeed Growth Stage Estimator Using Deep Convolutional Neural Networks
Teimouri, N., Dyrmann, M., Nielsen, P. R., Mathiassen, S. K., Somerville, G. J., & Jørgensen, R. N. (2018) · Sensors · doi:10.3390/s18051580 · Cited by 130
“This ability to extract thousands of features automatically means that convolutional neural networks are able to classify images collected in uncontrolled conditions with a significantly lower error rate than previous classifier methods [23].”
BackgroundMulti-label transfer learning for the early diagnosis of breast cancer
Chougrad, H., Zouaki, H., & Alheyane, O. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.112 · Cited by 130
Partial Discharge Classification Using Deep Learning Methods—Survey of Recent Progress
Pereira, S. R. B., Buldain-Pérez, J. D., Comech, M. P., Gilbert, I. P., & Orue, I. (2019) · Energies · doi:10.3390/en12132485 · Cited by 129
“To perform this task, the algorithm has to be able to recognize features (edges, curves, ridges) and their compositions [13].”
MethodInfluentialMartins, V. S., Kaleita, A. L., Gelder, B., da Silveira, H. L. F., & Abe, C. A. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.08.004 · Cited by 128
New avenues in artificial-intelligence-assisted drug discovery
Cerchia, C., & Lavecchia, A. (2023) · Drug Discovery Today · doi:10.1016/j.drudis.2023.103516 · Cited by 130
Autonomous surface crack identification of concrete structures based on the YOLOv7 algorithm
Ye, G., Qu, J., Tao, J., Dai, W., Mao, Y., & Jin, Q. (2023) · Journal of Building Engineering · doi:10.1016/j.jobe.2023.106688 · Cited by 128
COV-ECGNET: COVID-19 detection using ECG trace images with deep convolutional neural network
Rahman, T., Akinbi, A., Chowdhury, M. E. H., Rashid, T. A., Şengür, A., Khandakar, A. A., Islam, K. R., & Ismael, A. M. (2022) · Health Information Science and Systems · doi:10.1007/s13755-021-00169-1 · Cited by 127
Unsupervised Learning Of Sparse Features For Scalable Audio Classification.
Henaff, M., Jarrett, K., Kavukcuoglu, K., & LeCun, Y. (2011) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1416085 · Cited by 128
Self-citationDeep Learning Classification of 3.5-GHz Band Spectrograms With Applications to Spectrum Sensing
Lees, W. M., Wunderlich, A., Jeavons, P., Hale, P. D., & Souryal, M. R. (2019) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2019.2899871 · Cited by 126
An augmented reality application for improving shopping experience in large retail stores
Cruz, E., Orts‐Escolano, S., Gomez‐Donoso, F., Rizo-Maestre, C., Rangel, J. C., Mora, H., & Cazorla, M. (2018) · Virtual Reality · doi:10.1007/s10055-018-0338-3 · Cited by 126
“The use of DL techniques is considered a notable milestone in the research areas of computer vision and robotics (LeCun et al. 2010).”
MethodKapil, A., Meier, A., Zuraw, A., Steele, K. E., Rebelatto, M. C., Schmidt, G., & Brieu, N. (2018) · Scientific Reports · doi:10.1038/s41598-018-35501-5 · Cited by 101
“More specially, two fully supervised convolutional neural networks (CNN) 25,26 were independently trained on the complete manual annotations of 200 and 170 tissue slides respectively.”
MethodRahman, H., Bukht, T. F. N., Ahmad, R. B., Almadhor, A. S., & Javed, A. R. (2023) · Computational Intelligence and Neuroscience · doi:10.1155/2023/7717712 · Cited by 124
“Convolutional neural networks (CNNs) are composed of multiple trainable stages that culminate in a supervised classifer and feature maps [62].”
BackgroundAdaptive Structural Fingerprints for Graph Attention Networks
Zhang, K., Zhu, Y., Wang, Y.-X., & Zhang, J. (2020) · International Conference on Learning Representations · Cited by 123
Abdi, N., Albaseer, A. M., & Abdallah, M. M. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3354045 · Cited by 127
“3) Convolutional Neural Networks: Convolutional neural networks (CNNs) are a powerful type of neural network that has revolutionized the field of computer vision [110].”
BackgroundNew Deep Neural Nets for Fine-Grained Diabetic Retinopathy Recognition on Hybrid Color Space
Vo, H. H., & Verma, A. (2016) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2016.0049 · Cited by 124
Poletaev, I., Tokarev, M. P., & Первунин, К. С. (2019) · International Journal of Multiphase Flow · doi:10.1016/j.ijmultiphaseflow.2019.103194 · Cited by 123
Review of Deep Learning Based Automatic Segmentation for Lung Cancer Radiotherapy
Liu, X., Li, K., Yang, R., & Geng, L. (2021) · Frontiers in Oncology · doi:10.3389/fonc.2021.717039 · Cited by 122
Miccio, L. A., & Schwartz, G. A. (2020) · Polymer · doi:10.1016/j.polymer.2020.122341 · Cited by 121
Ghodrati, M., Khaligh‐Razavi, S., & Lehky, S. R. (2017) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2017.06.002 · Cited by 122
“The first to implement this architecture was the Neocognitron model (Fukushima,1980,1988), followed by the ConvNet model (LeCun and Bengio, 1995; LeCun et al., 2010), the HMAX model (Ghodrati et al.”
Linkon, A. H. M., Labib, M. M., Hasan, T., Hossain, M. T., & Marium-E-Jannat (2021) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100582 · Cited by 120
Machine Learning Refined: Foundations, Algorithms, and Applications
Watt, J., Borhani, R., & Katsaggelos, A. (2016) · Cambridge University Press eBooks · doi:10.1017/cbo9781316402276 · Cited by 91
Exploring Deep Physiological Models for Nociceptive Pain Recognition
Thiam, P., Bellmann, P., Kestler, H. A., & Schwenker, F. (2019) · Sensors · doi:10.3390/s19204503 · Cited by 118
“The designed approach consisted of a 32 multi-layer Convolutional Neural Network (CNN) [13] combined with a single-layer 33”
MethodSun, R., Pang, Y., & Li, W. (2023) · Electronics · doi:10.3390/electronics12041024 · Cited by 120
Building extraction from remote sensing images using deep residual U-Net
Wang, H., & Miao, F. (2022) · European Journal of Remote Sensing · doi:10.1080/22797254.2021.2018944 · Cited by 117
“Each single-layer network has three stages: convolution, nonlinear transformation, and down sampling (LeCun et al., 2010).”
BackgroundIntelligent diagnosis of northern corn leaf blight with deep learning model
Shuai-qun, P. A. N., Qiao, J., Wang, R., Yu, H., Wang, C., Taylor, K. L., & Pan, H. (2022) · Journal of Integrative Agriculture · doi:10.1016/s2095-3119(21)63707-3 · Cited by 117
Gao, X., Yan, X., Gao, P., Gao, X., & Zhang, S. (2019) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.101711 · Cited by 115
“CNN is a neural network structure proposed by LeCun [45], and it is the current popular deep network.”
BackgroundMethodThe Fingerprints of Fraud: Evidence from Mexico’s 1988 Presidential Election
Cantú, F. (2019) · American Political Science Review · doi:10.1017/s0003055419000285 · Cited by 115
An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network
Shen, X., Zhang, J., Yan, C., & Zhou, H. (2018) · Scientific Reports · doi:10.1038/s41598-018-24204-6 · Cited by 115
“With the novel method, more and deeper features are extracted to enhance classification accuracy and add more classification types[19] [20].”
MethodHatipoğlu, N., & Bilgin, G. (2017) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-017-1630-1 · Cited by 114
Wang, L., Scott, K. A., & Clausi, D. A. (2017) · Remote Sensing · doi:10.3390/rs9050408 · Cited by 115
“A CNN normally contains multiple stages that learn the image features, followed by a stack of fully connected (FC) layers [40].”
BackgroundMethodFrequency Disturbance Event Detection Based on Synchrophasors and Deep Learning
Wang, W., Yin, H., Chen, C., Till, A., Yao, W., Deng, X., & Liu, Y. (2020) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2020.2971909 · Cited by 114
“Some popular non-linear activations functions include sigmoid, tanh [25] and rectified linear unit (ReLU) [26].”
BackgroundDeep CNN-based damage classification of milled rice grains using a high-magnification image dataset
Bhupendra, Moses, K., Miglani, A., & Kankar, P. K. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.106811 · Cited by 114
Emotion recognition from facial expression using deep convolutional neural network
Liliana, D. Y. (2019) · Journal of Physics: Conference Series · doi:10.1088/1742-6596/1193/1/012004 · Cited by 113
Saliency-Guided Deep Neural Networks for SAR Image Change Detection
Geng, J., Ma, X., Zhou, X., & Wang, H. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2913095 · Cited by 113
Scattering Networks for Hybrid Representation Learning
Oyallon, E., Zagoruyko, S., Huang, G., Komodakis, N., Lacoste-Julien, S., Blaschko, M. B., & Belilovsky, E. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2855738 · Cited by 112
“These architectures are designed as very deep cascades of non-linear end-to-end learnedmodules [32].”
BackgroundEfficient Processing of Distributed Acoustic Sensing Data Using a Deep Learning Approach
Shiloh, L., Eyal, A., & Giryes, R. (2019) · Journal of Lightwave Technology · doi:10.1109/jlt.2019.2919713 · Cited by 112
“What started as a tool for computer vision and image processing [10], has expanded to many other fields such as medicine [11], audio processing [12] as well as optics.”
BackgroundIlyas, N., Shahzad, A., & Kim, K. (2019) · Sensors · doi:10.3390/s20010043 · Cited by 112
“Crowd counting is defined as estimating or counting the number of people in an image or video [29,30].”
BackgroundRole of Big Data and Machine Learning in Diagnostic Decision Support in Radiology
Syeda-Mahmood, T. F. (2018) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2018.01.028 · Cited by 111
Lung nodules diagnosis based on evolutionary convolutional neural network
da Silva, G. L. F., Neto, O. P. D. S., Silva, A. C., de Paiva, A. C., & Gattass, M. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4480-9 · Cited by 110
The Scope of Earth-Observation to Improve the Consistency of the SDG Slum Indicator
Kuffer, M., Wang, J., Nagenborg, M., Pfeffer, K., Kohli, D., Sliuzas, R., & Persello, C. (2018) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi7110428 · Cited by 110
“When DCNNs are applied to map areas of deprived living conditions, the learning process is conducted directly on images without organizing pixels into columns of vectors so that the spatial configurations on images can be preserved through learning [61].”
MethodDeep learning: A primer for dentists and dental researchers
Mohammad‐Rahimi, H., Rokhshad, R., Bencharit, S., Krois, J., & Schwendicke, F. (2023) · Journal of Dentistry · doi:10.1016/j.jdent.2023.104430 · Cited by 110
Movie genre classification with Convolutional Neural Networks
Simões, G. S., Wehrmann, J., Barros, R. C., & Ruiz, D. D. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727207 · Cited by 109
“Convolutional Neural Networks (CNNs) [25] are a pow erful class of models with impressive results in image recog nition problems.”
BackgroundDeep Deconvolutional Networks for Scene Parsing
Mohan, R. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.4101 · Cited by 53
“The CNNs of LeCun et. al [24] are powerful feature detectors in which input data is subject to multiple layers of convolutions, non-linearities, and pooling (sub-sampling).”
BackgroundA smart tele-cytology point-of-care platform for oral cancer screening
Sunny, S. P., Baby, A., James, B. L., Balaji, D., Aparna, N. V., Rana, M. H., Gurpur, P., Skandarajah, A., D’Ambrosio, M. V., Ramanjinappa, R. D., et al. (2019) · PLoS ONE · doi:10.1371/journal.pone.0224885 · Cited by 108
“The Convolutional Neural Network (CNN) adopted in this study enables direct image input with the filters being trained to extract features automatically [21].”
MethodAyachi, R., Afif, M., Said, Y., & Atri, M. (2019) · Neural Processing Letters · doi:10.1007/s11063-019-10115-8 · Cited by 107
“To handle this challenge, we propose the use of the convolutional neural networks [8], a deep learning model commonly used to solve computer vision problems.”
MethodAttention mechanisms and deep learning for machine vision: A survey of the state of the artPreprint
Hafiz, A. M., Parah, S. A., & Bhat, R. U. A. (2021) · Research Square · doi:10.21203/rs.3.rs-510910/v1 · Cited by 108
Learning Across Scales - Multiscale Methods for Convolution Neural Networks
Haber, E., Ruthotto, L., Holtham, E., & Jun, S.-H. (2018) · AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11680 · Cited by 102
“CNNs have been a major field of research over the last years, after showing remarkable success, e.g., in classifying images of hand writing, natural images, videos (see, e.g., LeCun and Bengio; Krizhevsky, Sutskever, and Hinton; LeCun, Kavukcuoglu, and Farabet (1995; 2012; 2010) and references therein).”
BackgroundMethodInfluentialDeep computational pathology in breast cancer
Duggento, A., Conti, A., Mauriello, A., Guerrisi, M., & Toschi, N. (2020) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2020.08.006 · Cited by 106
“In particular, each neuron of this layer performs this operation on a spatially clustered, often strictly contiguous, group of the data it receives [37 – 39].”
BackgroundDeep learning from phylogenies to uncover the epidemiological dynamics of outbreaks
Voznica, J., Zhukova, A., Bošková, V., Saulnier, E., Lemoine, F., Moslonka‐Lefebvre, M., & Gascuel, O. (2022) · Nature Communications · doi:10.1038/s41467-022-31511-0 · Cited by 107
Hardware for machine learning: Challenges and opportunities
Sze, V., Chen, Y.-H., Emer, J., Suleiman, A., & Zhang, Z. (2018) · 2018 IEEE Custom Integrated Circuits Conference (CICC) · doi:10.1109/cicc.2018.8357072 · Cited by 97
Unsupervised Change Detection in Satellite Images Using Convolutional Neural Networks
de Jong, K. L., & Bosman, A. S. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851762 · Cited by 105
“In order to construct an effective DI, a convolutional neural network (CNN) [5] is used in this study.”
MethodDavari, N., Akbarizadeh, G., & Mashhour, E. (2021) · IEEE Transactions on Power Delivery · doi:10.1109/tpwrd.2021.3116489 · Cited by 105
RedEye: Analog ConvNet Image Sensor Architecture for Continuous Mobile Vision
LiKamWa, R., Hou, Y., Gao, Y., Polansky, M., & Zhong, L. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.31 · Cited by 61
Predictive coding as a model of cognition
Spratling, M. (2016) · Cognitive Processing · doi:10.1007/s10339-016-0765-6 · Cited by 104
“…several hierarchical models of invariant object recognition which employ alternating layers of neurons to form more specialised representations in one layer, and more invariant representations in the next layer (Fukushima, 1980; LeCun et al., 2010; Riesenhuber and Poggio, 1999; Serre et al., 2007).”
BackgroundMethodNeural representation for object recognition in inferotemporal cortex
Lehky, S. R., & Tanaka, K. (2016) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2015.12.001 · Cited by 142
Offline handwritten English character recognition based on convolutional neural network
Yuan, A., Bai, G., Jiao, L., & Liu, Y. (2012) · IAPR International Workshop on Document Analysis Systems (DAS) · doi:10.1109/das.2012.61 · Cited by 100
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.