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 101–200 of 1,001
Deep learning with non-medical training used for chest pathology identification
Bar, Y., Diamant, I., Wolf, L., & Greenspan, H. (2015) · SPIE Proceedings · doi:10.1117/12.2083124 · Cited by 290
“Keywords: Deep learning, classification, chest x-rays, convolutional neural networks.”
BackgroundPassGAN: A Deep Learning Approach for Password Guessing
Hitaj, B., Gasti, P., Ateniese, G., & Perez-Cruz, F. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-21568-2_11 · Cited by 290
ShiDianNao: shifting vision processing closer to the sensor
Du, Z., Fasthuber, R., Chen, T., Ienne, P., Li, L., Luo, T., Feng, X., Chen, Y., & Temam, O. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/2872887.2750389 · Cited by 148
Deep learning for misinformation detection on online social networks: a survey and new perspectives
Islam, M. R., Liu, S., Wang, X., & Xu, G. (2020) · Social Network Analysis and Mining · doi:10.1007/s13278-020-00696-x · Cited by 289
Complex-Valued Neural Networks: A Comprehensive Survey
Lee, C., Hasegawa, H., & Gao, S. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105743 · Cited by 289
Brain Tumor Analysis Using Deep Learning and VGG-16 Ensembling Learning Approaches
Younis, A., Qiang, L., Nyatega, C. O., Adamu, M. J., & Kawuwa, H. B. (2022) · Applied Sciences · doi:10.3390/app12147282 · Cited by 286
“Doctors assess a tumor individual using approximate value and instinct, threatening the patient’s life [39].”
BackgroundDeep Learning for fault detection in wind turbines
Helbing, G., & Ritter, M. (2018) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2018.09.012 · Cited by 278
Zheng, Y., Liu, Q., Chen, E., Ge, Y., & Zhao, J. L. (2016) · Frontiers of Computer Science · doi:10.1007/s11704-015-4478-2 · Cited by 273
“The input and output of each layer are called feature maps [13].”
BackgroundMethodInfluentialDeep learning in mammography and breast histology, an overview and future trends
Hamidinekoo, A., Denton, E., Rampun, A., Honnor, K., & Zwiggelaar, R. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.03.006 · Cited by 273
Gold volatility prediction using a CNN-LSTM approach
Vidal, A., & Kristjanpoller, W. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113481 · Cited by 272
Rigid-Motion Scattering for Texture Classification
Sifre, L., & Mallat, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.1687 · Cited by 272
Unsupervised pre-trained filter learning approach for efficient convolution neural network
Rehman, S. U., Tu, S., Waqas, M., Huang, Y., Rehman, O. U., Ahmad, B., & Ahmad, S. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.06.084 · Cited by 270
Souza, J. C., Bandeira Diniz, J. O., Ferreira, J. L., França da Silva, G. L., Corrêa Silva, A., & de Paiva, A. C. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.06.005 · Cited by 261
Tropical Cyclone Intensity Estimation Using a Deep Convolutional Neural Network
Pradhan, R., Aygun, R. S., Maskey, M., Ramachandran, R., & Cecil, D. J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2766358 · Cited by 259
“Successful applications of convolutional neural networks for image recognition with high accuracy [9], [19]–[23], motivated us using convolutional neural network for hurricane intensity analysis.”
MethodWeakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detection
Zhang, F., Du, B., Zhang, L., & Xu, M. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2569141 · Cited by 257
“scenes [18].”
Classification of lung sounds using convolutional neural networks
Aykanat, M., Kılıç, Ö., Kurt, B., & Saryal, S. (2017) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-017-0213-2 · Cited by 256
Gong, W., Chen, H., Zhang, Z., Zhang, M., Wang, R., Guan, C., & Wang, Q. (2019) · Sensors · doi:10.3390/s19071693 · Cited by 251
“The input and output of each stage are sets of matrices called feature maps [37].”
BackgroundBrain Tumor Detection Using Deep Neural Network and Machine Learning Algorithm
Siar, M., & Teshnehlab, M. (2019) · 2019 9th International Conference on Computer and Knowledge Engineering (ICCKE) · doi:10.1109/iccke48569.2019.8964846 · Cited by 247
Yin, F., Lin, Z., Kong, Q., Xu, Y., Li, D., Theodoridis, S., & Cui, S. R. (2020) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2020.3036276 · Cited by 247
“However, there exist a plethora of deep variants for data with unique features, such as convolutional networks [58] and capsule networks [59] for images, long-short-term-memory (LSTM) networks for sequential data, and graph neural networks [60] for spatial and spatio-temporal data.”
BackgroundSAR Image segmentation based on convolutional-wavelet neural network and markov random field
Duan, Y., Liu, F., Jiao, L., Zhao, P., & Zhang, L. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.11.015 · Cited by 244
Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data
Alakwaa, F. M., Chaudhary, K., & Garmire, L. X. (2018) · Journal of Proteome Research · doi:10.1021/acs.jproteome.7b00595 · Cited by 244
A convolutional neural network neutrino event classifier
Aurisano, A., Radovic, A., Rocco, D., Himmel, A., Messier, M. D., Niner, E., Pawloski, G., Psihas, F., Sousa, A., & Vahle, P. (2016) · Journal of Instrumentation · doi:10.1088/1748-0221/11/09/p09001 · Cited by 240
“In this paper we will focus on CNNs, which have been highly successful in the field of computer vision for classification and other tasks [25, 30].”
MethodDong, Y., Jiang, Z., Shen, H., David Pan, W., Williams, L. A., Reddy, V. V. B., Benjamin, W. H., & Bryan, A. W. (2017) · 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI) · doi:10.1109/bhi.2017.7897215 · Cited by 237
“In this work, three well-known deep convolutional neural networks, including LeNet-5 [8], [9], AlexNet [10] and GoogLeNet [11] were used to learn the inherent features of the malaria infected cells and the non-infected cells.”
MethodEvaluating the Energy Efficiency of Deep Convolutional Neural Networks on CPUs and GPUs
Li, D., Chen, X., Becchi, M., & Zong, Z. (2016) · 2016 IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Social Computing and Networking (SocialCom), Sustainable Computing and Communications (SustainCom) (BDCloud-SocialCom-SustainCom) · doi:10.1109/bdcloud-socialcom-sustaincom.2016.76 · Cited by 236
“We then study how the network topology and the setting of the batch size and of several hardware parameters (hyper-threading, ECC, and DVFS) affect performance and energy efficiency (Section V and VI).”
BackgroundLin, Z., Ji, K., Kang, M., Leng, X., & Zou, H. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2698213 · Cited by 234
“Then, a simple convolutional highway network can be constructed by convolutional highway layers and Maxpool layers [16].”
Parallel Distributed Processing at 25: Further Explorations in the Microstructure of Cognition
Rogers, T. T., & McClelland, J. L. (2014) · Cognitive Science · doi:10.1111/cogs.12148 · Cited by 233
Multiple Kernel Learning for Hyperspectral Image Classification: A Review
Gu, Y., Chanussot, J., Jia, X., & Benediktsson, J. A. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2729882 · Cited by 233
“Among these methods, DNN [26]–[30] derived from neural network [31]–[37] has been successfully developed in computer vision [38]–[42] and has recently attracted more attention for HSI classification [43]–[45].”
MethodDeep Convolutional Neural Networks for mental load classification based on EEG data
Jiao, Z., Gao, X., Wang, Y., Li, J., & Xu, H. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.12.002 · Cited by 227
Recognition of peripheral blood cell images using convolutional neural networks
Acevedo, A., Alférez, S., Merino, A., Puigví, L., & Rodellar, J. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105020 · Cited by 224
Convolution in Convolution for Network in Network
Pang, Y., Sun, M., Jiang, X., & Li, X. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2676130 · Cited by 222
Joint Multi-person Pose Estimation and Semantic Part Segmentation
Xia, F., Wang, P., Chen, X., & Yuille, A. L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.644 · Cited by 221
“Specifically, we first extract human bounding boxes with Faster R-CNN [26], and resize the image region within each detection box following [33] so that small people are enlarged and extra large people are shrunk to a fixed size.”
BackgroundInfluentialDeep roto-translation scattering for object classification
Oyallon, E., & Mallat, S. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298904 · Cited by 138
“A convolutional network is a multilayer architecture, which cascades spatial convolutions and pooling operators, which includes sub-samplings [13].”
BackgroundAn investigation of XGBoost-based algorithm for breast cancer classification
Liew, X. Y., Hameed, N., & Clos, J. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100154 · Cited by 221
Radiological images and machine learning: Trends, perspectives, and prospects
Zhang, Z., & Sejdić, E. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.02.017 · Cited by 216
“Some outstanding frameworks such as the restricted Boltzmann machine [77], convolutional neural networks (CNNs) [78] and sparse autoencoders have proven useful tools in many applications such as Alzheimer’s disease diagnosis [79], segmentation [80], and tissue classification [81].”
MethodZhao, B., Ding, R., Chen, S., Linares-Barranco, B., & Tang, H. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2362542 · Cited by 216
“The event-driven ConvNets have a similar architecture with the conventional frame-driven ConvNets [20], where convolution and subsampling modules interlace.”
MethodInfluentialBeyond Manual Tuning of Hyperparameters
Hutter, F., Lücke, J., & Schmidt-Thieme, L. (2015) · KI - Künstliche Intelligenz · doi:10.1007/s13218-015-0381-0 · Cited by 215
“, [14]), or deep convolutional neural networks (CNNs; [38, 40]) have shown state-of-the-art performance (see [54] for a recent review).”
BackgroundTransductive Semi-Supervised Deep Learning Using Min-Max Features
Shi, W., Gong, Y., Ding, C., Ma, Z., Tao, X., & Zheng, N. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_19 · Cited by 215
“Some works use unlabeled data to pre-train DCNN models in an unsupervised way, and then fine-tune the models on labeled data [33–36].”
MethodNeural Models for Information RetrievalPreprint
Mitra, B., & Craswell, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.01509 · Cited by 220
“Convolutional layers are typically followed by pooling or fully-connected layers that perform a global aggregation over all the window instances.”
BackgroundGórriz, J. M., Álvarez-Illán, I., Álvarez-Marquina, A., Arco, J. E., Atzmueller, M., Ballarini, F., Barakova, E., Bologna, G., Bonomini, P., Castellanos-Dominguez, G., et al. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101945 · Cited by 214
Bezgin, D. A., Buhendwa, A. B., & Adams, N. A. (2022) · Computer Physics Communications · doi:10.1016/j.cpc.2022.108527 · Cited by 214
“Starting from applications in computer vision [21, 22], cognitive sciences [23], and genomics [24], machine learning and data-driven methods have also become more and more popular in physical and engineering sciences.”
BackgroundTang, S., Zhu, Y., & Yuan, S. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101406 · Cited by 210
Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering
Kazemi, V., & Elqursh, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03162 · Cited by 130
“Convolutional neural networks (CNNs) [16] have revo-lutionalized the field of computer vision in the recent years.”
BackgroundHuman action recognition using genetic algorithms and convolutional neural networks
Ijjina, E. P., & Chalavadi, K. M. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.012 · Cited by 209
“in [24,25] is the most popular deep neural network model in use for computer vision problems.”
BackgroundArtificial Neural Networks for Microwave Computer-Aided Design: The State of the Art
Feng, F., Na, W., Jin, J., Zhang, J., Zhang, W., & Zhang, Q.-J. (2022) · IEEE Transactions on Microwave Theory and Techniques · doi:10.1109/tmtt.2022.3197751 · Cited by 208
“Each stage usually includes three different layers: a convolutional layer, a nonlinearity layer, and a pooling layer [84], [145].”
BackgroundDeep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Pérez‐Cruz, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07464 · Cited by 205
“Deep learning models perform extremely well with correlated data, which contributed to substantial improvements in computer vision [45], image processing, video processing, face recognition [80], speech recognition [33], text-to-speech systems [62] and natural language processing [2, 14, 88].”
BackgroundDeep learning for precision agriculture: A bibliometric analysis
Coulibaly, S., Kamsu-Foguem, B., Kamissoko, D., & Traoré, D. (2022) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2022.200102 · Cited by 203
Scaling the Scattering Transform: Deep Hybrid Networks
Oyallon, E., Belilovsky, E., & Zagoruyko, S. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.599 · Cited by 202
“These architectures are designed as very deep cascades of non-linear end-to-end learned modules [22].”
Machine Learning for Financial Risk Management: A Survey
Mashrur, A., Luo, W., Zaidi, N. A., & Robles-Kelly, A. (2020) · IEEE Access · doi:10.1109/access.2020.3036322 · Cited by 200
“Interested readers can find a comprehensive review of Convolutional networks and their application in computer vision in [47].”
BackgroundAutomated detection and monitoring of methane super-emitters using satellite data
Schuit, B. J., Maasakkers, J. D., van der Bijl, P., Mahapatra, G., den Berg, A.-W. V., Pandey, S., Lorente, A., Borsdorff, T., Houweling, S., Varon, D. J., et al. (2023) · Atmospheric chemistry and physics · doi:10.5194/acp-23-9071-2023 · Cited by 204
“A max-pooling layer scans the previous layer with a 2× 2 kernel and returns the maximum value, thereby creating a feature map at half the resolution that is focused on dominant features (LeCun et al., 2010).”
BackgroundMethodInfluentialConvolutional Neural Networks for Human Activity Recognition Using Body-Worn Sensors
Moya Rueda, F., Grzeszick, R., Fink, G. A., Feldhorst, S., & Ten Hompel, M. (2018) · Informatics · doi:10.3390/informatics5020026 · Cited by 196
“By stacking them, and downsampling their outputs, CNNs extract more complex and abstract features, being at the same time invariant to distortions and translations [26].”
BackgroundDetecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise Reduction
Liang, B., Li, H., Su, M., Li, X., Shi, W., & Wang, X. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2018.2874243 · Cited by 196
“DEEP neural networks (DNNs) [1] have beenwidely adopted inmany applications such as computer vision [2], [3], speech recognition [4], [5], and natural language processing [6], [7].”
BackgroundLi, X., Pang, T., Xiong, B., Liu, W., Liang, P., & Wang, T. (2017) · 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2017.8301998 · Cited by 195
“level abstractions from raw data [27].”
Implementation of Training Convolutional Neural Networks
Liu, T., Fang, S., Zhao, Y., Wang, P., & Zhang, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.01195 · Cited by 123
Speaker identification features extraction methods: A systematic review
Tirumala, S. S., Shahamiri, S. R., Garhwal, A. S., & Wang, R. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.08.015 · Cited by 194
Hardware for machine learning: Challenges and opportunities
Sze, V., Chen, Y.-H., Emer, J., Suleiman, A., & Zhang, Z. (2017) · 2017 IEEE Custom Integrated Circuits Conference (CICC) · doi:10.1109/cicc.2017.7993626 · Cited by 193
Simulated Annealing Algorithm for Deep Learning
Rere, L. M. R., Fanany, M. I., & Arymurthy, A. M. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.12.114 · Cited by 192
Deep Over-sampling Framework for Classifying Imbalanced Data
Ando, S., & Huang, C. Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-71249-9_46 · Cited by 190
“We trained two instances of a basic CNN architecture [22] by back-propagation respectively with the original and the imbalanced data.”
MethodDeep learning improves macromolecule identification in 3D cellular cryo-electron tomograms
Moebel, E., Martinez-Sanchez, A., Lamm, L., Righetto, R. D., Wietrzynski, W., Albert, S., Larivière, D., Fourmentin, E., Pfeffer, S., Ortiz, J., et al. (2021) · Nature Methods · doi:10.1038/s41592-021-01275-4 · Cited by 189
“It is now well established that deep learning 9 produces state-of-the-art results in various fields (e.g. computer vision 10 , language processing 11 , image classification 12 and segmentation 13 , and object recognition 14 ).”
BackgroundRedEye: analog ConvNet image sensor architecture for continuous mobile vision
LiKamWa, R., Hou, Y., Gao, J., Polansky, M., & Zhong, L. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001164 · Cited by 189
“We design RedEye to compute continuous mobile vision tasks using Convolutional Neural Networks, also called ConvNets, for their efficacy in state-of-the-art object detection, handwriting recognition, and face detection [18].”
MethodIntraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations
Gunduz, H., Yaslan, Y., & Cataltepe, Z. (2017) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.09.023 · Cited by 188
An experimental study of speech emotion recognition based on deep convolutional neural networks
Zheng, W. Q., Yu, J. S., & Zou, Y. X. (2015) · 2015 International Conference on Affective Computing and Intelligent Interaction (ACII) · doi:10.1109/acii.2015.7344669 · Cited by 187
“Hence spatially translating the input of a feature detection layer will translate the output but leave it otherwise unchanged [24].”
BackgroundBubba, T. A., Kutyniok, G., Lassas, M., März, M., Samek, W., Siltanen, S., & Srinivasan, V. (2019) · Inverse Problems · doi:10.1088/1361-6420/ab10ca · Cited by 127
“One should stress that numerous network architectures exist, with convolutional neural networks (CNNs) [28, 62] being the most prominent design in the context of imaging [56, 63, 69].”
BackgroundDeep Convolutional Neural Network-Based Approaches for Face Recognition
Almabdy, S., & Elrefaei, L. (2019) · Applied Sciences · doi:10.3390/app9204397 · Cited by 185
“Figure 1 A typical convolutional network architecture [23].”
BackgroundMethodInfluentialApplication of Various YOLO Models for Computer Vision-Based Real-Time Pothole Detection
Park, S.-S., Tran, V. T., & Lee, D. (2021) · Applied Sciences · doi:10.3390/app112311229 · Cited by 183
Progressive Reconstruction of Visual Structure for Image Inpainting
Li, J., He, F., Zhang, L., Du, B., & Tao, D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00606 · Cited by 182
“There have been significant improvements in image inpainting through the use of deep learning [11].”
BackgroundJadhav, P., Rajguru, G., Datta, D., & Mukhopadhyay, S. (2020) · Biocybernetics and Biomedical Engineering · doi:10.1016/j.bbe.2020.01.010 · Cited by 181
Retail sales forecasting with meta-learning
Ma, S., & Fildes, R. (2021) · European Journal of Operational Research · doi:10.1016/j.ejor.2020.05.038 · Cited by 180
“…end, in this research, inspired by the deep feature learning for image classification (Bengio, Courville, & Vincent, 2013; LeCun & Bengio, 1995; LeCun, Kavukcuoglu, & Farabet, 2010), we design a meta-learning framework based on convolutional neural networks which can learn a supervised feature…”
BackgroundMethodCharoenkwan, P., Nantasenamat, C., Hasan, M. M., Manavalan, B., & Shoombuatong, W. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab133 · Cited by 179
Multiscale Scattering For Audio Classification.
Andén, J., & Mallat, S. (2011) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1415749 · Cited by 179
Automatic LPI Radar Waveform Recognition Using CNN
Kong, S.-H., Kim, M., Hoang, L. M., & Kim, E. (2018) · IEEE Access · doi:10.1109/access.2017.2788942 · Cited by 178
“In general, CNN shows a superb performance in image classification problems such as handwriting recognition and various object recognition including human faces, license plates, hand gesture, logos, and texts [22].”
BackgroundConvolutional neural network-based PSO for lung nodule false positive reduction on CT images
da Silva, G. L. F., Valente, T. L. A., Silva, A. C., de Paiva, A. C., & Gattass, M. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.05.006 · Cited by 178
A learning-based framework for miRNA-disease association identification using neural networks
Peng, J., Hui, W., Li, Q., Chen, B., Hao, J., Jiang, Q., Shang, X., & Wei, Z. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz254 · Cited by 178
Real-Time Facemask Recognition with Alarm System using Deep Learning
Militante, S. V., & Dionisio, N. V. (2020) · IEEE Control and System Graduate Research Colloquium (ICSGRC) · doi:10.1109/icsgrc49013.2020.9232610 · Cited by 176
Fan, G., Han, Y.-Y., Li, J., Peng, L., Yeh, Y., & Hong, W. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122012 · Cited by 176
Deep learning based FACS Action Unit occurrence and intensity estimation
Gudi, A., Tasli, H. E., den Uyl, T. M., & Maroulis, A. (2015) · 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG) · doi:10.1109/fg.2015.7284873 · Cited by 175
“The 44 × 44 output image produced by this layer is then passed to a max-pooling layer [17] of kernel size 3×3 with a stride of 2 in each dimension.”
MethodCerebral cortex : principles of operation
Rolls, E. T. (2016) · doi:10.82444/warw.33712699 · Cited by 175
Tang, S., Zhu, Y., & Yuan, S. (2022) · Advanced Engineering Informatics · doi:10.1016/j.aei.2022.101554 · Cited by 175
From smart to deep: Robust activity recognition on smartwatches using deep learning
Bhattacharya, S., & Lane, N. D. (2016) · 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops) · doi:10.1109/percomw.2016.7457169 · Cited by 174
Image-based defect detection in lithium-ion battery electrode using convolutional neural networks
Badmos, O., Kopp, A., Bernthaler, T., & Schneider, G. (2019) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-019-01484-x · Cited by 173
“Each unit in a feature map is connected to local patches in the feature maps of the previous layers through a set of weights called a filter bank (LeCun et al. 2010, 2015).”
BackgroundMethodInfluentialFacial Emotion Expressions in Human–Robot Interaction: A Survey
Rawal, N., & Stock‐Homburg, R. (2022) · International Journal of Social Robotics · doi:10.1007/s12369-022-00867-0 · Cited by 174
“CNN: Convolutional Networks [68] were invented in 1989 [67].”
BackgroundTufail, A. B., Ma, Y.-K., Kaabar, M. K. A., Martínez, F., Junejo, A. R., Ullah, I., & Khan, R. (2021) · Computational and Mathematical Methods in Medicine · doi:10.1155/2021/9025470 · Cited by 143
“Unsupervised and semisu-pervised learning can help in this direction by o ff ering potential solutions that help us in delving deeper into cancer pathogenesis and prediction tasks [170].”
BackgroundInvariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet
Rolls, E. T. (2012) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2012.00035 · Cited by 172
“With multiple stages, a ConvNet can learn multi-level hierarchies of features (LeCun et al., 2010).”
BackgroundPredicting Ion Mobility Collision Cross-Sections Using a Deep Neural Network: DeepCCS
Plante, P.-L., Francovic-Fontaine, É., May, J. C., McLean, J. A., Baker, E. S., Laviolette, F., Marchand, M., & Corbeil, J. (2019) · Analytical Chemistry · doi:10.1021/acs.analchem.8b05821 · Cited by 172
Pricing Options and Computing Implied Volatilities using Neural Networks
Liu, S., Oosterlee, C. W., & Bohté, S. M. (2019) · Risks · doi:10.3390/risks7010016 · Cited by 176
Abd-Ellah, M. K., Awad, A. I., Khalaf, A. A. M., & Hamed, H. F. A. (2018) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-018-0332-4 · Cited by 170
Diabetic retinopathy detection using deep convolutional neural networks
Doshi, D., Shenoy, A., Sidhpura, D., & Gharpure, P. (2016) · 2016 International Conference on Computing, Analytics and Security Trends (CAST) · doi:10.1109/cast.2016.7914977 · Cited by 169
“CNNs also consider the hierarchical representation of images while training by stacking multiple trainable stages on each other [2].”
BackgroundOrigami: A 803-GOp/s/W Convolutional Network Accelerator
Cavigelli, L., & Benini, L. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2592330 · Cited by 169
“Convolutional networks (ConvNets) are a prime example of this powerful, yet conceptually simple paradigm [8], [9].”
BackgroundClassification with scattering operators
Bruna, J., & Mallat, S. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995635 · Cited by 167
“A scattering vector is computed with a cascade of convolutions and modulus operators over m+ 1 layers, like in convolution network architectures [6, 1]:”
MethodA Survey for Cervical Cytopathology Image Analysis Using Deep Learning
Rahaman, M. M., Li, C., Wu, X., Yao, Y., Hu, Z., Jiang, T., Li, X., & Qi, S. (2020) · IEEE Access · doi:10.1109/access.2020.2983186 · Cited by 167
“In supervised learning, the CNN model is determined to generate hierarchical data features from a given labeled image dataset to accurately classify the cells into normal and abnormal [35].”
MethodA Review on Multiscale-Deep-Learning Applications
Elizar, E., Zulkifley, M. A., Muharar, R., Zaman, M. H. M., & Mustaza, S. M. (2022) · Sensors · doi:10.3390/s22197384 · Cited by 170
“CNN is a model that utilizes feed-forward networks with many hidden layers that are mostly used to extract spatial features for image-processing and object-detection applications [8].”
MethodCamacho-Collados, J., & Pilehvar, M. T. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5406 · Cited by 164
“Soon after their successful application to computer vision (LeCun et al., 2010; Krizhevsky et al., 2012), CNNs were ported to NLP for their desirable sensitivity to spatial structure of data which makes them effective in capturing semantic or syntactic patterns of word sequences (Goldberg, 2016).”
MethodImage inpainting based on deep learning: A review
Zhang, X., Zhai, D., Li, T., Zhou, Y., & Lin, Y. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.08.033 · Cited by 164
Learning Invariant Feature Hierarchies
LeCun, Y. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33863-2_51 · Cited by 164
“There have been numerous applications of convolutional networks going back to the mid 1990’s for such applications as OCR and handwriting recognition, face, person, and license plate detection, age and gender estimation, video surveillance, etc (see [21] and references therein).”
BackgroundSelf-citationHajiRassouliha, A., Taberner, A. J., Nash, M. P., & Nielsen, P. M. F. (2018) · Signal Processing: Image Communication · doi:10.1016/j.image.2018.07.007 · Cited by 126
Classification of Mammogram Images Using Multiscale all Convolutional Neural Network (MA-CNN)
Agnes, S. A., Anitha, J., Pandian, S. I. A., & Peter, J. D. (2020) · Journal of Medical Systems · doi:10.1007/s10916-019-1494-z · Cited by 162
“Whereas the convolutional neural network does not require hand-crafted features; it learns the feature directly from the image and classify the images using the trained CNN model [9, 10].”
MethodSeed-per-pod estimation for plant breeding using deep learning
Uzal, L. C., Grinblat, G. L., Namías, R., Larese, M. G., Bianchi, J. S., Morandi, E. N., & Granitto, P. M. (2018) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2018.04.024 · Cited by 163
Multi-Channel Deep Feature Learning for Intrusion Detection
Andresini, G., Appice, A., Mauro, N. D., Loglisci, C. A. A. M. D., & Malerba, D. (2020) · IEEE Access · doi:10.1109/access.2020.2980937 · Cited by 166
“A CNN is able to produce a good internal representation of the world by successfully capturing (spatial and/or temporal) dependencies (e.g. edges, colours, gradient orientation) in data through the application of relevant filters [42].”
What Do We Understand About Convolutional Networks?Preprint
Hadji, I., & Wildes, R. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08834 · Cited by 165
“oyed in recent computer vision applications are inspired by the successful architecture proposed by LeCun in 1998, now known as LeNet, for handwriting recognition [91]. As described in key literature [77,93], a classical convolutional network is made of four basic layers of processing: (i) a convolution layer, (ii) a…”
MethodInfluentialExtracting psychiatric stressors for suicide from social media using deep learning
Du, J., Zhang, Y., Luo, J., Jia, Y., Wei, Q., Tao, C., & Xu, H. (2018) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-018-0632-8 · Cited by 161
“in various computer vision tasks [25], CNN also demonstrated excellent performance in many NLP tasks, including various text classification tasks [26–29].”
BackgroundXiong, Z., Nash, M. P., Cheng, E., Fedorov, V. V., Stiles, M. K., & Zhao, J. (2018) · Physiological Measurement · doi:10.1088/1361-6579/aad9ed · Cited by 161
“Neural networks have been applied in many different fields, including medicine and bioengineering, to overcome the issues above by automating the feature extraction step (LeCun and Bengio 1995, LeCun et al 2010, 2015, Krizhevsky et al 2012).”
Method
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.