Deep Learning for Computer Vision: A Brief Review
Open accessThe DOI matches its Crossref record; 91 of the 93 references it cites were found in a registry or an index, and 2 are not checked yet.
Abstract
Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


![Figure 3 Denoising autoencoder [56].](https://figures.cochat.ai/paper-figures/9aa1be9726aa42d8bb9d1688c7960fe1/deep-learning-for-computer-vision-a-brief-review-figure-3.jpg)
![Figure 4 Object detection results comparison from [66]. (a) Ground truth; (b) bounding boxes obtained with [32]; (c) bounding boxes obtained with [66].](https://figures.cochat.ai/paper-figures/09358fc96d304df490ea4a5567b56ba6/deep-learning-for-computer-vision-a-brief-review-figure-4.jpg)
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Additionally, HAR with image/video processing has been extensively studied in the computer vision community [79,80], and the methodologies commonly used differ significantly from techniques used for IMUs, EEG, PPG, etc.”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [79]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 4×
“In [95], the authors propose a multimodal multistream deep learning framework to tackle the egocentric activity recognition problem, using both the video and sensor data and employing a dual CNNs and Long Short-Term Memory architecture.”
BackgroundInfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
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 · cited 2×
“In an attempt to compare these models (for a summary see Table 2), we can say that CNNs have generally performed better than DBNs in current literature on benchmark computer vision datasets such as MNIST.”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Research works printed but not linked: 21
- LeCun Y. Boser B. Denker J. Touretzky D. Handwritten digit recognition with a back-propagation network Advances in Neural Information Processing Systems 2 (NIPS∗89) 1990 Denver, CO, USA
- Frederic B. Lamblin P. Pascanu R. Theano: new features and speed improvements Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop 2012 http://deeplearning.net/software/theano/
- Chen X. Yuille A. L. Articulated pose estimation by a graphical model with image dependent pairwise relations Proceedings of the NIPS 2014
- Boureau Y. L. Ponce J. LeCun Y. A theoretical analysis of feature pooling in visual recognition Proceedings of the ICML 2010
- Krizhevsky A. Sutskever I. Hinton G. E. Imagenet classification with deep convolutional neural networks Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS '12) December 2012 Lake Tahoe, Nev, USA 1097 1105 2-s2.0-84876231242
- Smolensky P. Information processing in dynamical systems: Foundations of harmony theory In Parallel Distributed Processing: Explorations in the Microstructure of Cognition 1986 1 Cambridge, MA, USA MIT Press 194 281
- Hinton G. E. Sejnowski T. J. Learning and Relearning in Boltzmann Machines 1986 1 Cambridge, MA MIT Press p. 4.2
- Carreira-Perpinan M. A. Hinton G. E. On contrastive divergence learning Proceedings of the tenth international workshop on artificial intelligence and statistics., NP: Society for Artificial Intelligence and Statistics 2005 33 40
- Hinton G. A practical guide to training restricted Boltzmann machines Momentum 2010 9 p. 926
- Salakhutdinov R. Larochelle H. Efficient learning of deep Boltzmann machines Proceedings of the AISTATS 2010
- Salakhutdinov R. Hinton G. An efficient learning procedure for deep Boltzmann machines Neural Computation 2012 24 8 1967 2006 MR2978160 10.1162/NECO_a_00311 Zbl1247.68223 2-s2.0-84874125782 22509963 · DOI · Paper page
- Salakhutdinov R. Hinton G. A better way to pretrain Deep Boltzmann Machines Proceedings of the 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 December 2012 usa 2447 2455 2-s2.0-84877755914
- Goodfellow I. Mirza M. Courville A. Multi-prediction deep Boltzmann machines Proceedings of the NIPS 2013
- Vincent P. Larochelle H. Bengio Y. Manzagol P.-A. Cohen W. W. McCallum A. Roweis S. T. Extracting and composing robust features with denoising autoencoders in Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML'08) 2008 ACM 1096 1103
- Gallinari P. LeCun Y. Thiria S. Fogelman-Soulie F. Memoires associatives distribuees Proceedings of the in Proceedings of COGNITIVA 87 1987 Paris, La Villette
- Bengio Y. Lamblin P. Popovici D. Larochelle H. Sch B. Platt J. and. Hoffman T. Schölkopf B. Greedy layer-wise training of deep networks Advances in Neural Information Processing Systems (NIPS06) 2007 19 MIT Press 153 160
- Hosang J. Benenson R. Schiele B. How good are detection proposals, really? Proceedings of the 25th British Machine Vision Conference, BMVC 2014 September 2014 gbr 2-s2.0-84919779754
- Nair V. Hinton G. E. 3D object recognition with deep belief nets Proceedings of the NIPS 2009
- Kitsikidis A. Dimitropoulos K. Douka S. Grammalidis N. Dance analysis using multiple kinect sensors Proceedings of the 9th International Conference on Computer Vision Theory and Applications, VISAPP 2014 January 2014 prt 789 795 2-s2.0-84906896563
- Jain A. Tompson J. Andriluka M. Learning human pose estimation features with convolutional networks Proceedings of the ICLR 2014
- Tompson J. J. Jain A. LeCun Y. Joint training of a convolutional network and a graphical model for human pose estimation Proceedings of the NIPS 2014
Cited by
Items 601–700 of 1,008
Girdler, B., Moon, H., Bae, M. R., Ryu, S. S., Bae, J., & Yu, M. S. (2021) · International Forum of Allergy & Rhinology · doi:10.1002/alr.22854 · Cited by 48
“33,34 However, this requirement is often challenging to meet with medical image recordings due to costs and limitations of the number of specific cases.”
BackgroundEgger, J., Pepe, A., Gsaxner, C., Jin, Y., Li, J., & Kern, R. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.773 · Cited by 52
Sound Actions: Conceptualizing Musical Instruments
Jensenius, A. R. (2022) · The MIT Press eBooks · doi:10.7551/mitpress/14220.001.0001 · Cited by 71
Goh, K. W., Surono, S., Afiatin, M. Y. F., Mahmudah, K. R., Irsalinda, N., Chaimanee, M., & Onn, C. W. (2024) · Emerging Science Journal · doi:10.28991/esj-2024-08-02-014 · Cited by 42
“In the context of image classification, DL methods are often the first choice [4].”
MethodAutomatic detection of urban flood level with YOLOv8 using flooded vehicle dataset
Wan, J., Qin, Y., Shen, Y., Yang, T., Xu, Y., Zhang, S., Yang, G., Xue, F., & Wang, Q. J. (2024) · Journal of Hydrology · doi:10.1016/j.jhydrol.2024.131625 · Cited by 42
Xue, X., Zhang, J., & Chen, Y. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105730 · Cited by 42
Wu, Y., Peng, Z., Hu, Y., Wang, R., & Xu, T. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114497 · Cited by 48
Hybrid machine learning techniques based on genetic algorithm for heart disease detection
Kumar, A., Dhanka, S., Singh, J., Khan, A. A., & Maini, S. (2024) · Innovation and Emerging Technologies · doi:10.1142/s2737599424500087 · Cited by 46
Abir, S. I., Shoha, S., Hossain, M. M., Rahman, S. M., Saimon, S. I., Islam, I., Mamun, M. A. I., & Khan, N. I. (2024) · Journal of Computer Science and Technology Studies · doi:10.32996/jcsts.2024.6.5.13 · Cited by 42
Real-Time Semantic Segmentation for Fisheye Urban Driving Images Based on ERFNet
Sáez, Á., Bergasa, L. M., López-Guillén, E., Romera, E., Tradacete-Ágreda, M., Gómez-Huélamo, C., & Egido, J. D. (2019) · Sensors · doi:10.3390/s19030503 · Cited by 46
“The remarkable success of semantic segmentation solutions during the last few years has been closely related to the breakthrough of deep learning methods, which have proven to widely outperform previous state-of-the-art machine learning techniques [2,3].”
BackgroundRadiomics for Gleason Score Detection through Deep Learning
Brunese, L., Mercaldo, F., Reginelli, A., & Santone, A. (2020) · Sensors · doi:10.3390/s20185411 · Cited by 45
“We exploit convolutional neural networks (CNN) considering that they have demonstrated to have good prediction performances in the detection of simple patterns within data, which will then be used to form more complex patterns within higher layers [7].”
MethodArabic (Indian) digit handwritten recognition using recurrent transfer deep architecture
Alkhawaldeh, R. S. (2020) · Soft Computing · doi:10.1007/s00500-020-05368-8 · Cited by 42
Automatic Fault Mapping in Remote Optical Images and Topographic Data With Deep Learning
Mattéo, L., Manighetti, I., Tarabalka, Y., Gaucel, J., van den Ende, M., Mercier, A., Taşar, O., Girard, N., Leclerc, F., Giampetro, T., et al. (2021) · Journal of Geophysical Research Solid Earth · doi:10.1029/2020jb021269 · Cited by 48
“This has spawned numerous applications in computer vision, natural language processing, and behavioral analysis (Sturman et al., 2020; Voulodimos et al., 2018; Young et al., 2018).”
Huang, X., Zhu, D., Zhang, F., Liu, T., Li, X., & Zou, L. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3076630 · Cited by 47
“Most modern deep learning models are based on artificial neural networks, specifically convolutional neural networks (CNN) that were inspired by the visual system’s structure and hierarchically composed of input, output, and multiple hidden layers [36].”
BackgroundImagined character recognition through EEG signals using deep convolutional neural network
Ullah, S., & Halim, Z. (2021) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-021-02368-0 · Cited by 49
“Majority of the studies that employ deep learning for the classification of EEG signals do not use any noise removal technique [7, 12, 13, 47].”
BackgroundKienbaum, L., Abondano, M. C., Blas, R., & Schmid, K. (2021) · Plant Methods · doi:10.1186/s13007-021-00787-6 · Cited by 44
“The success of machine learning in image analysis can be attributed to the evolution of neural networks from simple architectures to advanced feature-extracting convolutional neural networks (CNNs) [64].”
BackgroundLanjewar, M. G., Morajkar, P. P., & Parab, J. S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12392-3 · Cited by 43
“In CV, CNNs have been successfully applied in various applications such as facial recognition, detection of objects, robotic power visualization, and self-driving cars [66].”
MethodZvuloni, E., Read, J., Ribeiro, A. H., Ribeiro, A. L. P., & Behar, J. A. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3239527 · Cited by 45
“In the computer vision field, it is the dominant or even exclusive approach for many datadriven tasks [4].”
BackgroundConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
Villarreal-Vasquez, M., & Bhargava, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.00711 · Cited by 22
“They have successfully been applied to solve problems in multiple areas such as natural language processing [1] and computer vision [2].”
BackgroundFace mask detection in COVID-19: a strategic review
Vibhuti, Jindal, N., Singh, H., & Rana, P. S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12999-6 · Cited by 41
“Deep Learning techniques have managed to pick up steam currently because of their ability to train vast data with high accuracy [102].”
BackgroundA review of non-invasive sensors and artificial intelligence models for diabetic foot monitoring
Kaselimi, M., Protopapadakis, E. E., Doulamis, A. D., & Doulamis, N. D. (2022) · Frontiers in Physiology · doi:10.3389/fphys.2022.924546 · Cited by 42
“Consequently, deep learning approaches occurred naturally as an application scenario in DFU monitoring, based on optical information (Voulodimos et al., 2018).”
BackgroundSelf-citationGao, Y., Li, Y., Jiang, R., Zhan, X., Lü, H., Guo, W., Yang, W., Ding, Y., & Liu, S. (2023) · Plant Phenomics · doi:10.34133/plantphenomics.0064 · Cited by 41
“In contrast, for plant phenotyping, this type of dataset rarely exists [19].”
BackgroundArtificial intelligence in rechargeable battery: Advancements and prospects
Xiong, Y., Zhang, D., Ruan, X., 蒋善宝, Zou, X., Yuan, W., Liu, X., Zhang, Y., Nie, Z., Wei, D., et al. (2024) · Energy storage materials · doi:10.1016/j.ensm.2024.103860 · Cited by 56
A Survey on Knowledge Editing of Neural Networks
Mazzia, V., Pedrani, A., Caciolai, A., Rottmann, K., & Bernardi, D. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3498935 · Cited by 52
“Over the last years, deep learning methods have been shown to outperform previous state-of-the-art techniques in several applications in the field [37], and while more “traditional” techniques are still relevant for some applications, neural networks-based approaches have become the de facto…”
Deep learning for waveform identification of resting needle electromyography signals
Nodera, H., Osaki, Y., Yamazaki, H., Mori, A., Izumi, Y., & Kaji, R. (2019) · Clinical Neurophysiology · doi:10.1016/j.clinph.2019.01.024 · Cited by 43
Deep learning acceleration of Total Lagrangian Explicit Dynamics for soft tissue mechanics
Meister, F., Passerini, T., Mihalef, V., Tüysüzoğlu, A., Maier, A., & Mansi, T. (2019) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2019.112628 · Cited by 43
Saha, A., Tso, S., Rabski, J., Sadeghian, A., & Cusimano, M. D. (2020) · Pituitary · doi:10.1007/s11102-019-01026-x · Cited by 44
“…of the manuscript. increasing applicability to develop sophisticated tools in various areas of data processing such as natural language processing (NLP) [2], computer vision (analyzing images or videos) [3–5], data mining [6, 7], robotics [8], gaming [9, 10], and big data in general [11].”
BackgroundIndustry 4.0 Lean Shopfloor Management Characterization Using EEG Sensors and Deep Learning
Schmidt, D., Villalba-Díez, J., Ordieres-Meré, J. B., Gevers, R., Schwiep, J., & Molina, M. (2020) · Sensors · doi:10.3390/s20102860 · Cited by 43
“This has made it a popular choice for many other fields such as computer vision [70], audio processing [71] or bioinformatics [72].”
BackgroundPredicting mechanically driven full-field quantities of interest with deep learning-based metamodels
Mohammadzadeh, S., & Lejeune, E. (2021) · Extreme Mechanics Letters · doi:10.1016/j.eml.2021.101566 · Cited by 47
Zhang, T., & Sun, S. (2021) · Energies · doi:10.3390/en14227724 · Cited by 41
“This technology has completely changed various fields of industry and academia, including computer vision [31], natural language translation and processing [32], electronic entertainment [33], etc. Compared with traditional machine learning methods, deep learning algorithms have made significant…”
BackgroundFuentes, A., Yoon, S., Lee, M. H., & Park, D. S. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.682230 · Cited by 47
“The massive accessibility of media and hardware technology has brought new opportunities for the application of deep learning into various research areas (Schmidhuber, 2015; Voulodimos et al., 2018).”
BackgroundA soft-sensor for sustainable operation of coagulation and flocculation units
Arab, M., Akbarian, H., Gheibi, M., Akrami, M., Fathollahi‐Fard, A. M., Hajiaghaei–Keshteli, M., & Tian, G. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105315 · Cited by 41
FAIR: Fair adversarial instance re-weighting
Petrović, A., Nikolić, M., Radovanović, S., Delibašić, B., & Jovanović, M. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.082 · Cited by 40
Ashwin, T. S., Prakash, V., & Rajendran, R. (2023) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2023.100125 · Cited by 48
Kwon, K.-Y., Park, A.-R., Lee, H., & Mun, D. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107903 · Cited by 40
Guo, Y., Zhong, D., Sun, H., Jiang, Z., Ye, L., Deng, Z., & Liu, H. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3319530 · Cited by 43
“In recent years, with the development of artificial intelligence technology, deep learning has obtained substantial performance in computer vision [14], natural language processing [15], speech recognition [16] and automatic driving [17], and it also brings a new perspective to signal processing.”
BackgroundGoyal, P., Rani, R., & Singh, K. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09301-6 · Cited by 46
“CNN can improve efficiency even further and demonstrate excellent performance in AD diagnosis without implementing handmade feature extraction because it does so automatically [20, 21].”
Mohana, M., & Subashini, P. (2024) · SN Computer Science · doi:10.1007/s42979-024-02792-7 · Cited by 44
“For instance, methods like HOG [1] and Viola-Jones [60, 151] are employed for feature extraction to identify faces or objects in images.”
Zhang, H., Falletta, N. J., Xie, J., Yu, R., Lee, S., Billah, S. M., & Carroll, J. M. (2024) · International ACM SIGGROUP Conference on Supporting Group Work (GROUP) · doi:10.1145/3688828.3699636 · Cited by 40
“With the development of technologies such as computer vision (CV) [37] and natural language processing (NLP) [20], applications that replace human vision by using electronic cameras or digital conversions to obtain information are becoming increasingly prevalent.”
DeepEvolution: A Search-Based Testing Approach for Deep Neural Networks
Braiek, H. B., & Khomh, F. (2019) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme.2019.00078 · Cited by 40
“Given the rapid progress and the impressive performance of DNNs in computer-vision tasks [7], we propose following”
BackgroundGuan, L., Liu, Z., Cai, L., & Yan, J. (2020) · Sensors · doi:10.3390/s20041158 · Cited by 40
“CNN is more effective in applications than many traditional classification methods [32].”
MethodYi, L., Le, A. V., Hayat, A. A., Borusu, C. S. C. S., Elara, M. R., Nhan, N. H. K., & Kandasamy, P. (2020) · IEEE Access · doi:10.1109/access.2020.3003376 · Cited by 40
“The difficulty in using deep learning is the high computational power [28] required as large networks”
BackgroundPlant diseases detection with low resolution data using nested skip connections
Pardede, H. F., Suryawati, E., Zilvan, V., Ramdan, A., Kusumo, R. B. S., Heryana, A., Yuwana, R. S., Krisnandi, D., Subekti, A., Fauziah, F., et al. (2020) · Journal Of Big Data · doi:10.1186/s40537-020-00332-7 · Cited by 41
“DL methods have been used in many machine learning tasks, such as speech recognition[12, 46] natural language processing[9, 48], and computer vision[56].”
MethodThuyet, D. Q., Kobayashi, Y., & Matsuo, M. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105727 · Cited by 40
Wu, R., Fujita, Y., & Soga, K. (2020) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2020.103558 · Cited by 40
WDA: An Improved Wasserstein Distance-Based Transfer Learning Fault Diagnosis Method
Zhu, Z., Wang, L., Peng, G., & Li, S. (2021) · Sensors · doi:10.3390/s21134394 · Cited by 42
“With the rise of machine learning, especially deep learning, more and more data-driven algorithms have been proposed and applied successfully in different fields in the last few years [1–3].”
Tutorial on the Use of Deep Learning in Diffuse Optical Tomography
Balasubramaniam, G. M., Wiesel, B., Biton, N., Kumar, R., Kupferman, J., & Arnon, S. (2022) · Electronics · doi:10.3390/electronics11030305 · Cited by 44
Detecting Buildings and Nonbuildings from Satellite Images Using U-Net
Alsabhan, W. M., Alotaiby, T. N., & Dudin, B. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/4831223 · Cited by 40
“Deep learning has hada significant impactoncomputer visionresearch in recent years [13].”
BackgroundA lightweight face-assisted object detection model for welding helmet use
Chen, W., Li, C., & Guo, H. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119764 · Cited by 40
DNN or k-NN: That is the Generalize vs. Memorize QuestionPreprint
Cohen, G., Sapiro, G., & Giryes, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06822 · Cited by 46
“…learning tools today, getting state-of-the-art results in many domains such as computer vision Krizhevsky et al. [2012], Schroff et al. [2015], Voulodimos et al. [2018], natural language processing Bahdanau et al. [2014], Kim [2014], and speech recognition Hinton et al. [2012], Zhang et al.…”
BackgroundGenetic Neural Architecture Search for automatic assessment of human sperm images
Miahi, E., Mirroshandel, S. A., & Nasr, A. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115937 · Cited by 39
“Moreover, in recent years, Convolutional Neural Network (CNN) algorithms became the state-of-the-art technique in solving a lot of computer vision tasks (Voulodimos et al., 2018), especially in the area of image classification (Krizhevsky et al.”
BackgroundRousseau, M., & Retrouvey, J.-M. (2022) · American Journal of Orthodontics and Dentofacial Orthopedics · doi:10.1016/j.ajodo.2021.03.017 · Cited by 46
Sahil, K., Mehta, P., Bhardwaj, S. K., & Dhaliwal, L. K. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-99714-0.00021-2 · Cited by 51
Deveci, B. U., Celtikoglu, M., Albayrak, Ö., Ünal, P., & Kirci, P. (2023) · Information Systems Frontiers · doi:10.1007/s10796-023-10371-z · Cited by 41
Multimodal deep learning for point cloud panoptic segmentation of railway environments
Grandío, J., Riveiro, B., Lamas, D., & Arias, P. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.104854 · Cited by 39
Maxwell, A. E., Odom, W. E., Shobe, C. M., Doctor, D. H., Bester, M. S., & Ore, T. M. (2023) · Earth and Space Science · doi:10.1029/2023ea002845 · Cited by 41
“CNN-based methods have enabled progress in computer vision (Hassaballah & Awad, 2020; Voulodimos et al., 2018), autonomous vehicle technologies (Fayyad et al.”
MethodUnleashing the potential: AI empowered advanced metasurface research
Fu, Y., Zhou, X., Yu, Y., Chen, J., Wang, S., Zhu, S. N., & Wang, Z. (2024) · Nanophotonics · doi:10.1515/nanoph-2023-0759 · Cited by 43
“AI has been widely applied in various aspects of our lives, from computer vision [61], [62], speech recognition [63], [64], and financial analysis [65], [66] to autonomous driving [67], intelligent disease diagnosis [68]–[71], and conversational models [72], [73].”
BackgroundZhang, C., Achuthan, A., & Himel, G. M. S. (2024) · IEEE Access · doi:10.1109/access.2024.3392595 · Cited by 45
“Over the last decade, deep learning has propelled ground-breaking developments across various domains such as computer vision and natural language processing [1] and uncovered extensive potential in the area of medical image analysis [2].”
BackgroundA two stage lightweight approach for intrusion detection in Internet of Things
Li, Z., & Yao, W. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124965 · Cited by 43
Zhao, N., Chen, Y., Cheng, L., & Chen, J. (2024) · Nonlinear Dynamics · doi:10.1007/s11071-024-10562-6 · Cited by 40
“The universal approximation and powerful performance of neural network (NN) have led to the success of deep learning [1] in numerous areas of artificial intelligence,includingimagerecognition[2],computer vision [3], and natural language translation [4].”
Dance Pose Identification from Motion Capture Data: A Comparison of Classifiers
Protopapadakis, E. E., Voulodimos, A. S., Doulamis, A. D., Camarinopoulos, S., Doulamis, N. D., & Miaoulis, G. (2018) · Technologies · doi:10.3390/technologies6010031 · Cited by 39
Self-citationMulti-Source Deep Transfer Neural Network Algorithm
Li, J., Wu, W., Xue, D., & Gao, P. (2019) · Sensors · doi:10.3390/s19183992 · Cited by 43
“Currently, machine learning is one of the fastest growing technologies located at the core of artificial intelligence and data science, which has been widely used in intrusion detection [2,3], speech recognition [4,5], computer vision [6,7], spam detection [8,9], pattern recognition [10], text classification [11], and…”
BackgroundGeoweaver: Advanced Cyberinfrastructure for Managing Hybrid Geoscientific AI Workflows
Sun, Z., Di, L., Burgess, A., Tullis, J. A., & Magill, A. B. (2020) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi9020119 · Cited by 41
“The lower computational time costs and drastically improved results have spurred the wide use of machine learning models, with application in many science disciplines, from speech recognition [14]; driverless cars [15]; to smart cities [16]; intelligent homes [17]; and many other fields such as agriculture, environmen…”
BackgroundMultipose Face Recognition-Based Combined Adaptive Deep Learning Vector Quantization
Sarhan, S. S., Nasr, A. A., & Shams, M. Y. (2020) · Computational Intelligence and Neuroscience · doi:10.1155/2020/8821868 · Cited by 39
“On the other hand, many researchers investigated using deep learning in face detection as in [24] a detailed survey of deep learning techniques is illustrated which is commonly classified to deep Boltzmann machine (DBM), deep belief neural network (DBN), auto encoder (AE), and Deep convolutional neural networks (DCNN).”
BackgroundBuilding Complex Seismic Velocity Models for Deep Learning Inversion
Ren, Y., Nie, L., Yang, S., Jiang, P., & Chen, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3051159 · Cited by 39
“The successful application examples in various computer vision tasks (e.g. [25]–[28]) indicates a great potential of DNN in dealing with the ill-posedness of seismic inversion problems.”
BackgroundPersonalized recommendation with knowledge graph via dual-autoencoder
Yang, Y., Zhu, Y. Q., & Li, Y. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02647-1 · Cited by 44
“…has been achieved by deep neural networks in feature representation learning on multiple disciplines like speech recognition [4], computer vision [5], and natural language processing [6], more and more recommendation systems based on deep neural networks have been proposed for alleviating…”
BackgroundPeng, L., Wang, C., Tian, G., Liu, G., Gan, L., Lu, Y., Yang, J., Chen, M., & Li, Z. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.995323 · Cited by 40
Nguyen, H., Ly, K. L., Lam, V. K., & Wang, Z. (2023) · Sensors · doi:10.3390/s23094209 · Cited by 40
“In contrast, unsupervised learning features of deep belief networks, deep Boltzmann machines, and stacked autoencoders can remove the need for labeled datasets [26].”
BackgroundMachine learning based screw drive state detection for unfastening screw connections
Assadi, A. A., Holtz, D., Nägele, F., Nitsche, C., Kraus, W., & Huber, M. F. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.07.013 · Cited by 40
Ferreira, R. E. P., Bresolin, T., Rosa, G. J. M., & Dórea, J. R. R. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107272 · Cited by 40
Chen, X., Zhang, K., Ji, Z., Shen, X., Liu, P., Zhang, L., Wang, J., & Yao, J. P. (2023) · Mathematics · doi:10.3390/math11214418 · Cited by 38
Applications of machine learning methods in kidney disease: hope or hype?
Chan, L., Vaid, A., & Nadkarni, G. N. (2020) · Current Opinion in Nephrology & Hypertension · doi:10.1097/mnh.0000000000000604 · Cited by 42
“An example is Deep Belief Networks that was applied to EEG interpretation and drug discovery.[5]”
MethodIslam, M. S., Sultana, M. S., Roy, U. K., & Mahmud, J. A. (2021) · Jurnal Ilmiah Teknik Elektro Komputer dan Informatika · doi:10.26555/jiteki.v6i2.18978 · Cited by 43
“A deep learning structure automatically operates in order to learn then represent data across different processing layers through specifically classifying specific input data or vine frames [30].”
BackgroundAdvanced Ultrasound and Photoacoustic Imaging in Cardiology
Wu, M., Awasthi, N., Rad, N. M., Pluim, J. P. W., & Lopata, R. G. P. (2021) · Sensors · doi:10.3390/s21237947 · Cited by 38
“Domain adaptation methods [165,166] could help in reducing the gap between the distribution of simulated data and real-PA data.”
BackgroundMaximized Frequency Doubling through the Inverse Design of Nonlinear Metamaterials
Raju, L., Lee, K.-T., Liu, Z., Zhu, D., Zhu, M., Poutrina, E., Urbas, A., & Cai, W. (2022) · ACS Nano · doi:10.1021/acsnano.1c09298 · Cited by 37
An Optimized CNN Model for Engagement Recognition in an E-Learning Environment
Hu, Y. Q., Jiang, Z., & Zhu, K. (2022) · Applied Sciences · doi:10.3390/app12168007 · Cited by 40
“In recent years, there have been many novel neural network structural models applied in various fields of computer vision [16,17].”
BackgroundAn Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-Based Gradients
Wiedmann, M., Hölle, M., Periyasamy, M., Meyer, N., Ufrecht, C., Scherer, D. D., Plinge, A., & Mutschler, C. (2023) · IEEE International Conference on Quantum Computing and Engineering (QCE) · doi:10.1109/qce57702.2023.00058 · Cited by 48
“M ACHINE learning (ML) has been the key driver for a great variety of recent technological advancements, for example in computer vision [1], natural language processing [2], automatic translation [3], self-driving cars [4], and medical diagnostics [5].”
BackgroundComputer Vision-Based Wood Identification: A Review
Silva, J., Bordalo, R., Pissarra, J., & de Palacios, P. (2022) · Forests · doi:10.3390/f13122041 · Cited by 37
Underwater fish mass estimation using pattern matching based on binocular system
Shi, C., Zhao, R., Liu, C., & Li, D. (2022) · Aquacultural Engineering · doi:10.1016/j.aquaeng.2022.102285 · Cited by 37
Li, H., Zou, L., Kowah, J. A. H., He, D., Wang, L., Yuan, M., & Liu, X. (2023) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-023-00558-y · Cited by 41
“Deep learning methods have been frequently employed in machine translation [5–7], computer vision [8–10], speech recognition [11–13], and text sentiment classification [14–17].”
MethodUsage of few-shot learning and meta-learning in agriculture: A literature review
Porto, J. V. D. A., Dorsa, A. C., Weber, V., Porto, K. R. D. A., & Pistori, H. (2023) · Smart Agricultural Technology · doi:10.1016/j.atech.2023.100307 · Cited by 42
Factor Augmented Sparse Throughput Deep ReLU Neural Networks for High Dimensional Regression
Fan, J.-Q., & Gu, Y. (2022) · Journal of the American Statistical Association · doi:10.1080/01621459.2023.2271605 · Cited by 56
“Deep learning (Goodfellow et al. 2016) has achieved tremendous empirical success in computer vision (Voulodimos et al. 2018), natural language processing (Otter, Medina, and Kalita 2020) and other statistical prediction tasks (LeCun, Bengio, and Hinton 2015) due to its representation power.”
Paiste, H. J., Godwin, R. C., Smith, A. D., Berkowitz, D. E., & Melvin, R. L. (2024) · Frontiers in Digital Health · doi:10.3389/fdgth.2024.1316931 · Cited by 41
“In terms of more simple image-based specialties, diagnostic radiology and pathology are the two clinical specialties were a most obvious entry-point for AI applications in healthcare, as they both utilize one of AI ’ s most well-vetted skills: deep learning for computer vision (9).”
BackgroundMalignant Melanoma Classification Using Cross-Platform Dataset with Deep Learning CNN Architecture
Mukherjee, S., Adhikari, A., & Roy, M. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-13-6783-0_4 · Cited by 37
Wang, D., Tian, F., Yang, S. X., Zhu, Z., Jiang, D., & Cai, B. (2020) · Sensors · doi:10.3390/s20030874 · Cited by 42
“NIR data has wide spectral band, serious overlap of spectral peak, and complex internal information characteristics, thus deep training is more suitable than shallow network (normally with one hidden layer) in processing complex information [22–24].”
BackgroundWürschinger, H., Mühlbauer, M., Winter, M. R., Engelbrecht, M., & Hanenkamp, N. (2020) · Procedia CIRP · doi:10.1016/j.procir.2020.01.121 · Cited by 39
Unified framework for quantum classification
Nghiem, N. A., Chen, S. Y.-C., & Wei, T.-C. (2021) · Physical Review Research · doi:10.1103/physrevresearch.3.033056 · Cited by 46
Liu, G., Zhou, W., Lan, T., Liu, W., Liu, Y., & Xu, H. (2021) · Sensors · doi:10.3390/s21113721 · Cited by 42
[Retracted] A Review of Intelligent Driving Pedestrian Detection Based on Deep Learning
Tian, D., Han, Y., Wang, B., Guan, T. M., & Wei, W. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/5410049 · Cited by 37
“In recent years, with the continuous development of deep learning [122, 123], object detection has made great progress, especially the wide application of multicategory datasets such as COCO.”
BackgroundRetractedJiao, M., Wan, G., Guo, Y., Wang, D., Liu, H., Xiang, J., & Liu, F. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.867466 · Cited by 39
“In recent years, deep learning has achieved great success in the fields of computer vision (Voulodimos et al., 2018), natural language processing (Young et al., 2018), bioinformatics (Min et al., 2017), etc., by employing its end-to-end feature extraction and representation capability (Deng and Yu,…”
BackgroundDeep learning method for predicting the strengths of microcracked brittle materials
Xu, B., Sang, Y., Li, M., Zhao, H., & Feng, X. (2022) · Engineering Fracture Mechanics · doi:10.1016/j.engfracmech.2022.108600 · Cited by 39
Li, Y., Xue, J., Wang, K., Zhang, M., & Li, Z. (2022) · Foods · doi:10.3390/foods11182915 · Cited by 41
Wire Harness Assembly Process Supported by a Collaborative Robot: A Case Study Focus on Ergonomics
Navas-Reascos, G. E., Romero, D., Rodriguez, C. A., Guedea-Elizalde, F., & Stahre, J. (2022) · Robotics · doi:10.3390/robotics11060131 · Cited by 37
Kong, J., Yang, C., Xiao, Y., Lin, S., Ma, K., & Zhu, Q. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/4391491 · Cited by 41
“In recent years, modern agriculture is striving to make full use of innovative systems and methods to achieve intelligent production and management, including Internet of Things (IoT), automated robots, big data cloud computing, and artificial intelligence modelling [7–11].”
BackgroundMEB-YOLO: An Efficient Vehicle Detection Method in Complex Traffic Road Scenes
Song, Y., Hong, S., Hu, C., He, P., Tao, L., Tie, Z., & Ding, C. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.038910 · Cited by 46
Wildfire risk assessment using deep learning in Guangdong Province, China
Jiang, W., Qiao, Y., Zheng, X., Zhou, J., Jiang, J., Meng, Q., Su, G., Zhong, S., & Wang, F. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.103750 · Cited by 56
Applications of Zeroing Neural Networks: A Survey
Wang, T., Zhang, Z., Huang, Y., Liao, B., & Li, S. (2024) · IEEE Access · doi:10.1109/access.2024.3382189 · Cited by 36
“Therapid development of neural networks has led to their widespread application across various fields, with out-standing performance observed in addressing static problems, including computer vision [4], natural language processing [5], and speech recognition [6].”
BackgroundArtificial intelligence in the diagnosis, treatment and prevention of urinary stones
Yang, B., Veneziano, D., & Somani, B. K. (2020) · Current Opinion in Urology · doi:10.1097/mou.0000000000000820 · Cited by 36
SGRNN-AM and HRF-DBN: a hybrid machine learning model for cricket video summarization
Shingrakhia, H., & Patel, H. N. (2021) · The Visual Computer · doi:10.1007/s00371-021-02111-8 · Cited by 36
Rao, J., Yang, F., Mo, H., Kollmannsberger, S., & Rank, E. (2022) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2022.117418 · Cited by 39
“For a detailed survey on CNNs, we refer to [26, 27, 28, 29].”
Background
Metadata
- Authors
- Voulodimos, A., Doulamis, N., Doulamis, A., & Protopapadakis, E.
- Affiliations
- National Technical University of Athens (GR)
- Corresponding author
- Voulodimos, Athanasios
- Venue
- Computational Intelligence and Neuroscience
- Publisher
- Wiley
- Published
- 2018
- Volume
- 2018
- Pages
- 1-13
- ISSN
- 1687-5265 (ISSN-L)
- 1687-5273
- PMC
- PMC5816885
- OpenAlex
- W2794284562
- Cited by
- 3,403
- References
- 56
- Citations by year
- 2026: 202 · 2025: 447 · 2024: 586 · 2023: 541 · 2022: 570 · 2021: 496 · 2020: 375 · 2019: 153 · 2018: 32
- FWCI
- 30.98
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Computational Intelligence and Neuroscience (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- State Scholarships Foundation
- European Social Fund
- Greek national funds
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- deep learning, computer vision, convolutional neural networks, deep Boltzmann machine, deep belief network, stacked denoising autoencoder, object detection, face recognition, human action recognition, activity recognition, human pose estimation
- MeSH terms
- Machine Learning, Algorithms, Humans, Neural Networks, Computer
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.