Object Detection With Deep Learning: A Review
Open accessThe DOI matches its Crossref record; 252 of the 252 references it cites were found in a registry or an index.
Abstract
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.
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
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“We ensure that these “hard” candidate genes are included in the candidate list for each patient during training, as using such “hard” examples tends to improve the efficiency of training113.”
From Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases (2025) · cites this paper as [113]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This capability makes YOLO exceptionally well-suited for applications requiring rapid decision-making, such as autonomous driving, medical diagnostics, and surveillance systems [8,9].”
From The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024) · cites this paper as [8]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Although great progress has been reported with respect to accuracy in object detection and recognition [173], current systems are mainly designed to calculate 2D or 3D bounding boxes for a couple of trained object classes, or to provide a segmented image of the driving environment.”
From A survey of deep learning techniques for autonomous driving (2020) · cites this paper as [173]
The cited source says what the claim attributes to it.
In the citing paper
“Deep learning methods are more effective and accurate, and they perform better in complex environments to detect objects [11].”
From Fusion of Deep Sort and Yolov5 for Effective Vehicle Detection and Tracking Scheme in Real-Time Traffic Management Sustainable System (2023) · cites this paper as [11]
In the citing paper
“Deep Compression uses three steps, prunning, quantization, and Huffman Encoding, to compress over-parameterized DNN models, such as VGG [77], AlexNet [1].”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [75]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 11×
“Recent state-of-the-art image classification networks, such as ResNets [47] and GoogLeNets [45], [93], are fully convolutional.”
BackgroundMethodInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 18×
“A typical CNN architecture, which is referred to as VGG16, can be found in Figure 2.”
BackgroundMethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 15×
“To address the problem of limited training data, Kummerer et al. [134] proposed the Deep Gaze by transferring from the AlexNet to generate a high-dimensional feature space and create a saliency map.”
BackgroundMethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster 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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 6×
“1) The emergence of large-scale annotated training data, such as ImageNet [39], to fully exhibit its very large learning capacity.”
BackgroundMethodInfluentialCortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Distinctive 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 2×
“This is due to the fact that these features can produce representations associated with complex cells in human brain [19].”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 23×
“3) SSD: YOLO has a difficulty in dealing with small objects in groups, which is caused by strong spatial constraints imposed on bounding box predictions [18].”
BackgroundMethodInfluential
Research works printed but not linked: 4
- wang, 2017, Face R-CNN
- 10.1109/ICCV.2015.221 · DOI · Paper page
- 10.1109/TPAMI.2009.167 · DOI · Paper page
- everingham, 2011, The pascal visual object classes challenge 2012 (voc2012) results (2012)
Cited by
Items 601–700 of 1,018
Du, X., Chen, Z., Li, Q., Yang, S., Jiang, L., Yang, Y., Li, Y., & Gu, Z. (2023) · Bio-Design and Manufacturing · doi:10.1007/s42242-022-00226-y · Cited by 67
“tion is to find all the objects of interest from the image and identify their category and location [57].”
BackgroundInfluentialWang, B., Wang, X., Wang, N., Javaheri, Z., Moghadamnejad, N., & Abedi, M. (2023) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2023.100876 · Cited by 57
Bag of Strategies Set New State-of-the-art for Algae Object Detectors
Yang, Z., Wen, H., Wei, Z., & Zhang, Z. (2022) · International Conference on Universal Village (UV) · doi:10.1109/uv56588.2022.10185474 · Cited by 57
“Object Detection is a task of precisely estimating the concepts and locations of objects in each image [28], [29].”
BackgroundInstruction-driven fusion of Infrared–visible images: Tailoring for diverse downstream tasks
Yang, Z., Zhang, Y., Li, H., & Liu, Y. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103148 · Cited by 68
Plant species recognition methods using leaf image: Overview
Zhang, S., Huang, W., Huang, Y., & Zhang, C. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.09.113 · Cited by 57
Enabling autonomous scanning probe microscopy imaging of single molecules with deep learning
Sotres, J., Boyd, H., & Gonzalez-Martinez, J. F. (2021) · Nanoscale · doi:10.1039/d1nr01109j · Cited by 65
HSV Color-Space-Based Automated Object Localization for Robot Grasping without Prior Knowledge
Kang, H., Han, H., Bae, H., Kim, M., Son, J.-Y., & Kim, Y. (2021) · Applied Sciences · doi:10.3390/app11167593 · Cited by 60
“To minimize external environmental changes, deep learning algorithms such as R-CNN [36], Fast R-CNN [37], and YOLO [38] have attracted attention in recent years [39–41].”
BackgroundMethodNing, H., Li, Z., Ye, X., Wang, S., Wang, W., & Huang, X. (2021) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2021.1981334 · Cited by 56
Prediction of Stock Price Using Statistical and Ensemble learning Models: A Comparative Study
Durgapal, A., & Vimal, V. (2021) · IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) · doi:10.1109/upcon52273.2021.9667644 · Cited by 56
YOLOv5-Based Vehicle Detection Method for High-Resolution UAV Images
Chen, Z., Cao, L., & Wang, Q. (2022) · Mobile Information Systems · doi:10.1155/2022/1828848 · Cited by 56
“Convolutional neural networks have been increasingly used in the object detection field [16, 17].”
MethodA Survey on Unbalanced Classification: How Can Evolutionary Computation Help?
Pei, W., Xue, B., Zhang, M., Shang, L., Yao, X., & Zhang, Q. (2023) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2023.3257230 · Cited by 67
“In computer vision, object detection [257] is targeted at identifying objects of interest in an image.”
BackgroundPre-sensor computing with compact multilayer optical neural network
Zheng, H., Shi, W., Wu, S., Wang, Y., Yang, S., & Chen, H. (2024) · Science Advances · doi:10.1126/sciadv.ado8516 · Cited by 63
DiCENet: Dimension-Wise Convolutions for Efficient Networks
Mehta, S., Hajishirzi, H., & Rastegari, M. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3041871 · Cited by 64
Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA
Shymkovych, V., Telenyk, S., & Kravets, P. I. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05706-3 · Cited by 56
Application of Deep Learning and Unmanned Aerial Vehicle on Building Maintenance
Kung, R.-Y., Pan, N.-H., Wang, C. C. N., & Lee, P. (2021) · Advances in Civil Engineering · doi:10.1155/2021/5598690 · Cited by 62
“Algorithms can determine the class of image features or objects and detect and label the objects within the image usually by placing a rectangular bounding box, indicating the algorithm’s confidence of existence [64].”
BackgroundFPGA Implementation of Object Detection Accelerator Based on Vitis-AI
Wang, J., & Gu, S. (2021) · International Conference on Information Science and Technology · doi:10.1109/icist52614.2021.9440554 · Cited by 69
“Compared with the previous algorithms, especially for small targets, the accuracy has been significantly improved in [8] [9].”
ResultU-Net based neural network for fringe pattern denoising
Gurrola-Ramos, J., Dalmau, O., & Alarcón, T. E. (2021) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2021.106829 · Cited by 56
A light defect detection algorithm of power insulators from aerial images for power inspection
Yang, L., Fan, J., Song, S., & Liu, Y. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07437-5 · Cited by 61
“With the high-performance computing hardware, object detection and identification have achieved huge breakthroughs combined with deep learning [24].”
BackgroundA Survey of SAR Image Target Detection Based on Convolutional Neural Networks
Zhang, Y., & Hao, Y. (2022) · Remote Sensing · doi:10.3390/rs14246240 · Cited by 58
TransU-Net++: Rethinking attention gated TransU-Net for deforestation mapping
Jamali, A., Roy, S. K., Li, J., & Ghamisi, P. (2023) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2023.103332 · Cited by 75
Vision + X: A Survey on Multimodal Learning in the Light of Data
Zhu, Y., Wu, Y., Sebe, N., & Yan, Y. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3420239 · Cited by 80
“Moreover, the applications of computer vision in the image domain have been extensively extended and enriched from simple image classifications [216], [216] to various task scenarios like object detection [310] and segmentation [154] within the image.”
BackgroundHoang, T. M., Nam, S. H., & Park, K. R. (2019) · IEEE Access · doi:10.1109/access.2019.2933598 · Cited by 67
“These models can realize high accuracy rates, but typically require more computational time than one-stage methods (approximately 2 s for extracting 2k region proposals [29]).”
BackgroundMethodA Robust Method for Wheatear Detection Using UAV in Natural Scenes
He, M.-X., Peng, H., & Xin, Y.-Z. (2020) · IEEE Access · doi:10.1109/access.2020.3031896 · Cited by 56
“into three steps: region selection, feature extraction of candidate region, and classifier classification [18].”
Transfer learning enables prediction of CYP2D6 haplotype function
McInnes, G., Dalton, R., Sangkuhl, K., Whirl‐Carrillo, M., Lee, S., Tsao, P. S., Gaedigk, A., Altman, R. B., & Woodahl, E. L. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008399 · Cited by 58
Cheng, D., Hsieh, T., Yen, K., & Kao, C. (2021) · Diagnostics · doi:10.3390/diagnostics11030518 · Cited by 56
“The CNN has been used for more than 10 years to extract features [25].”
MethodTullu, A., Endale, B., Wondosen, A., & Hwang, H.-Y. (2021) · Applied Sciences · doi:10.3390/app11104706 · Cited by 64
Visual-based obstacle detection and tracking, and conflict detection for small UAS sense and avoid
Opromolla, R., & Fasano, G. (2021) · Aerospace Science and Technology · doi:10.1016/j.ast.2021.107167 · Cited by 54
Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
Alsentzer, E., Li, M. M., Kobren, S. N., Noori, A., Undiagnosed Diseases Network, Kohane, I. S., & Zitnik, M. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01749-1 · Cited by 54
Li, G., Li, C., Wu, G., Ji, D., & Zhang, H. (2021) · IEEE Access · doi:10.1109/access.2021.3084360 · Cited by 54
“Nowadays, deep learning has achieved excellent performance in various computer vision tasks, such as image classi-fication [2], object detection [3], and image segmentation [4].”
BackgroundOne-stage CNN detector-based benthonic organisms detection with limited training dataset
Chen, T., Wang, N., Wang, R., Zhao, H., & Zhang, G. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.08.014 · Cited by 54
Yang, B., Zhang, B., Zhang, Q., Wang, Z., Dong, M., & Fang, T. (2022) · Structure and Infrastructure Engineering · doi:10.1080/15732479.2022.2039217 · Cited by 54
“Object detection is a method to precisely estimate the concepts and locations of objects contained in each image to gain a complete image understanding (Zhao et al. 2019).”
BackgroundMethodAhmadian, H., Mageswaran, P., Walter, B. A., Blakaj, D. M., Bourekas, E. C., Mendel, E., Marras, W. S., & Soghrati, S. (2022) · International Journal for Numerical Methods in Biomedical Engineering · doi:10.1002/cnm.3601 · Cited by 62
Koopman-Based MPC With Learned Dynamics: Hierarchical Neural Network Approach
Wang, M., Lou, X., Wu, W., & Cui, B. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3194958 · Cited by 54
“It is known that numerous methods based on deep learning have been proposed for application in different fields, such as natural language processing [29], biomedical processor [30], and object detection [31], which reflect the extensive effective applicability of deep learning methods.”
BackgroundE-waste management using hybrid optimization-enabled deep learning in IoT-cloud platform
Ramya, P., Ramya, V., & Markapudi, B. R. (2022) · Advances in Engineering Software · doi:10.1016/j.advengsoft.2022.103353 · Cited by 54
Zarei, N., Moallem, P., & Shams, M. (2022) · IEEE Access · doi:10.1109/access.2022.3221942 · Cited by 60
“They are excellent at learning image features and can perform various tasks related to classification and bounding box regression [5].”
An Improved Algorithm for Wind Turbine Blade Defect Detection
Ran, X., Zhang, S., Wang, H., & Zhang, Z. (2022) · IEEE Access · doi:10.1109/access.2022.3216613 · Cited by 59
“The one-stage detection algorithm reconstructs object detection as a single regression problem, directly from image pixels to bounding box coordinates and class probabilities [22], [23].”
MethodMCDCNet: Multi-scale constrained deformable convolution network for apple leaf disease detection
Liu, B., Huang, X., Sun, L., Wei, X., Ji, Z., & Zhang, H. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109028 · Cited by 60
Edge Computing-Driven Real-Time Drone Detection Using YOLOv9 and NVIDIA Jetson Nano
Hakani, R., & Rawat, A. (2024) · Drones · doi:10.3390/drones8110680 · Cited by 67
Shrimp recognition using ShrimpNet based on convolutional neural network
Hu, W.-C., Wu, H.-T., Zhang, Y.-F., Zhang, S., & Lo, C.-H. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-01727-3 · Cited by 54
Salhaoui, M., Molina, J. C. M., González, A. G., Arioua, M., & Ortiz, F. J. (2020) · Remote Sensing · doi:10.3390/rs12121981 · Cited by 59
“Being one of the main computer vision issues, object detection is capable of providing useful insights for the semantic understanding of images and videos [81].”
BackgroundText Detection and Recognition in the Wild: A ReviewPreprint
Raisi, Z., Naiel, M. A., Fieguth, P., Wardell, S., & Zelek, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04305 · Cited by 66
“er understanding of what type of features are useful for constructing improved text detection and recognition models. For example, a ResNet [148] with higher number of layers will give better results [46,191], while it is not clear yet what can be an efficient feature extractor that allows differentiating text from oth…”
BackgroundFew shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
(2022) · doi:10.1101/2022.12.07.22283238 · Cited by 54
Detection of a Moving UAV Based on Deep Learning-Based Distance Estimation
Lai, Y., & Huang, Z.-Y. (2020) · Remote Sensing · doi:10.3390/rs12183035 · Cited by 58
“In contrast to traditional object detection methods, detectors using deep learning are able to learn semantic, high-level, and deeper features to address the problems existing in traditional architectures [17].”
BackgroundDeep Learning-Based Algal Detection Model Development Considering Field Application
Park, J., Baek, J.-W., Kim, J., You, K., & Kim, K. (2022) · Water · doi:10.3390/w14081275 · Cited by 55
Yousefi, M., Rafie, A. S. M., Al-Haddad, S. A. R., & Azrad, S. (2022) · IEEE Access · doi:10.1109/access.2022.3194507 · Cited by 59
Chen, H., Hou, L., Zhang, G., & Wu, S. (2022) · Safety Science · doi:10.1016/j.ssci.2022.105958 · Cited by 55
Solder Joint Inspection on Printed Circuit Boards: A Survey and a Dataset
Ülger, F., Yüksel, S. E., Yılmaz, A., & Gökcen, D. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3277935 · Cited by 53
“Therefore, YOLOv5 is applied to localize and classify IC and capacitor’s internal errors from thermal PCB images that can reveal internal characteristics of components [97]. d) Fine-grained classification: Another approach to the inspection task can be fine-grained image classification (FGIC).”
BackgroundInfluentialSynchronizing Object Detection: Applications, Advancements and Existing Challenges
Hosain, M. T., Zaman, A., Abir, M. R., Akter, S., Mursalin, S., & Khan, S. S. (2024) · IEEE Access · doi:10.1109/access.2024.3388889 · Cited by 70
Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects
Roy, D. B., Alison, J., August, T., Bélisle, M., Bjerge, K., Bowden, J. J., Bunsen, M. J., Cunha, F., Geissmann, Q., Goldmann, K., et al. (2024) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2023.0108 · Cited by 64
Yu, Y., Yang, X., Li, Q., Da, F., Dai, Y., Qiao, Y., & Yan, J. (2024) · 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/cvpr52733.2024.01588 · Cited by 72
“Beyond horizontal detection [24, 58], oriented object detection [38] has received extensive attention.”
BackgroundDental Images Recognition Technology and Applications: A Literature Review
Prados‐Privado, M., Villalón, J. G., Martínez-Martínez, C. H., & Ivorra, C. (2020) · Applied Sciences · doi:10.3390/app10082856 · Cited by 53
Cheng, H., Yu, H., Zeng, P., Osipov, E., Li, S., & Vyatkin, V. V. (2020) · Sensors · doi:10.3390/s20195659 · Cited by 56
“The Conv layer is the key functional block of a CNN, which convolutes a filter matrix with values from a receptive field of neurons [37] and finally extracts representative features from input data.”
BackgroundOrchard Mapping with Deep Learning Semantic Segmentation
Anagnostis, A., Tagarakis, A. C., Katerıs, D., Moysiadis, V., Sørensen, C. A. G., Pearson, S., & Bochtis, D. (2021) · Sensors · doi:10.3390/s21113813 · Cited by 55
“Object detection algorithms differ because they predict the location of objects and assign the appropriate class to them [16].”
BackgroundLearning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
He, Y., Gao, F., Wang, J., Hussain, A., Yang, E., & Zhou, H. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3068530 · Cited by 55
“Recently, with the development of deep learning theories and the substantial improvement of the hardware, deep convolutional neural network (DCNN)-based algorithms have achieved great success in computer vision fields, such as target detection, recognition, segmentation, tracking, and so on [24]–[31].”
BackgroundFull-Resolution Quality Assessment for Pansharpening
Scarpa, G., & Ciotola, M. (2022) · Remote Sensing · doi:10.3390/rs14081808 · Cited by 54
“In recent years, a paradigm shift from model-based to data-driven approaches has revolutionized all fields of image processing, from computer vision [34, 20, 28, 39, 96] to remote sensing [91, 65, 13, 47].”
BackgroundUsing Deep Learning for Collecting Data about Museum Visitor Behavior
Ferrato, A., Limongelli, C., Mezzini, M., & Sansonetti, G. (2022) · Applied Sciences · doi:10.3390/app12020533 · Cited by 65
A Review of Vision-Laser-Based Civil Infrastructure Inspection and Monitoring
Zhou, H., Xu, C., Tang, X., Wang, S., & Zhang, Z. (2022) · Sensors · doi:10.3390/s22155882 · Cited by 56
“Object detection aims to distinguish different objects and accurately estimate the position and concept of the object in the image [36].”
BackgroundMonitoring and Identification of Road Construction Safety Factors via UAV
Zhu, C., Zhu, J., Bu, T., & Gao, X. (2022) · Sensors · doi:10.3390/s22228797 · Cited by 61
Kim, H.-S., Park, D.-W., Kim, S.-I., Oh, G.-H., & Kim, H. (2023) · Composites Part B Engineering · doi:10.1016/j.compositesb.2023.110694 · Cited by 52
Improved GBS-YOLOv5 algorithm based on YOLOv5 applied to UAV intelligent traffic
Liu, H., Duan, X., Lou, H., Gu, J. J., Chen, H., & Bi, L. (2023) · Scientific Reports · doi:10.1038/s41598-023-36781-2 · Cited by 55
“Due to the two-stage is based on the classification of the target detection algorithm, the detection speed is slow 47 , and still can not meet most of the requirements of real-time places.”
BackgroundALADA: A lite automatic data augmentation framework for industrial defect detection
Wang, Y., Chung, S., Khan, W. A., Wang, T., & Xu, D. J. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102205 · Cited by 52
CFAR-DP-FW: A CFAR-Guided Dual-Polarization Fusion Framework for Large-Scene SAR Ship Detection
Zeng, T., Zhang, T., Shao, Z., Xu, X., Zhang, W., Shi, J., Wei, S., & Zhang, X. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3358058 · Cited by 55
“According to the research works of computer vision community [32], [33], [34], CNN-based algorithms can be divided into one-stage algorithms and two-stage algorithms.”
MethodKajabad, E. N., & Ivanov, S. V. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.08.209 · Cited by 52
Vorugunti, C. S., Pulabaigari, V., Gorthi, R. K., & Mukherjee, P. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.05.072 · Cited by 52
Collaborative Attention-Based Heterogeneous Gated Fusion Network for Land Cover Classification
Li, X., Lei, L., Sun, Y., Li, M., & Kuang, G. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3015389 · Cited by 53
“…deep convolutional neural networks (DCNNs) as the powerful feature extractors have achieved superior performance in the computer vision tasks [14], [15], which use the layer-by-layer nonlinear transformation to intelligently extract deep semantic features from raw images, and then relieve the…”
BackgroundBarbosa, R. C., Ayub, M. S., Rosa, R. L., Rodríguez, D. Z., & Wuttisittikulkij, L. (2020) · Sensors · doi:10.3390/s20216218 · Cited by 67
“In addition, studies tested the tuning of parameters to improve the performance of Faster R-CNN on vehicle detection [39].”
BackgroundMethodInfluentialText query based summarized event searching interface system using deep learning over cloud
Kumar, K. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10157-4 · Cited by 52
Improved Vision-Based Detection of Strawberry Diseases Using a Deep Neural Network
Kim, B., Han, Y., Park, J.-H., & Lee, J. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2020.559172 · Cited by 61
“Many visual feature classifiers have been developed for application in many problem domains (Zhao et al., 2019).”
BackgroundMemory Manipulations in Extended Reality
Bonnail, E., Tseng, W.-J., Mcgill, M., Lecolinet, E., Huron, S., & Gugenheimer, J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580988 · Cited by 51
“However, research in the direction of object detection and identifcation in images made a lot of progress these last years [132, 139].”
Machine‐Learning‐Assisted Intelligent Imaging Flow Cytometry: A Review
Luo, S., Shi, Y., Chin, L. K., Hutchinson, P. E., Zhang, Y., Chierchia, G., Talbot, H., Jiang, X., Bourouina, T., & Liu, A. Q. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100073 · Cited by 52
Image Manipulation Localization Using Attentional Cross-Domain CNN Features
Li, S., Xu, S., Ma, W., & Zong, Q. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3130168 · Cited by 58
“Recently, deep learning has shown promising performance in numerous computer vision tasks, such as object detection, semantic segmentation, and image classification [10], [11].”
BackgroundSelf-citationOpportunities for Human-AI Collaboration in Remote Sighted Assistance
Lee, S., Yu, R., Xie, J., Billah, S. M., & Carroll, J. M. (2022) · 27th International Conference on Intelligent User Interfaces · doi:10.1145/3490099.3511113 · Cited by 39
“The challenge motivates us to resort to AI-based object detection algorithms [124], which are able to detect small objects.”
BackgroundYu, B., Yang, A., Chen, F., Wang, N., & Wang, L. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102930 · Cited by 51
Deep Learning Approach For Objects Detection in Underwater Pipeline Images
Gašparović, B., Lerga, J., Mauša, G., & Ivašić-Kos, M. (2022) · Applied Artificial Intelligence · doi:10.1080/08839514.2022.2146853 · Cited by 59
“The CNN can be divided into two main categories (Zhao et al. 2019): Region Proposal-Based Framework (two-stage) and Regression/ Classification-Based Framework (one-stage).”
MethodArtificial Intelligence in Veterinary Imaging: An Overview
Pereira, A. I., Franco-Gonçalo, P., Leite, P., Ribeiro, A., Alves‐Pimenta, S., Colaço, B., Loureiro, C., Gonçalves, L., Filipe, V. M. D. J., & Ginja, M. (2023) · Veterinary Sciences · doi:10.3390/vetsci10050320 · Cited by 55
“Object detection refers to the task of estimating the concept and localization of an object of interest within the images [28].”
BackgroundHan, Y., Wang, C., Luo, H., Wang, H., Chen, Z., Xia, Y., & Yun, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-07021-6 · Cited by 62
“…the following characteristics: (1) they occupy only a few pixels in the image; (2) high-frequency details, such as texture information, boundary cues, and color, exhibit substantial variations and are highly susceptible to interference from current imaging conditions and complex backgrounds 18 .”
Automated Detection of Plant Diseases Using Image Processing and Faster R-CNN Algorithm
Cynthia, S. T., Hossain, K. M. S., Hasan, M. N., Asaduzzaman, M., & Das, A. K. (2019) · International Conference on Sustainable Technologies for Industry 5.0 (STI) · doi:10.1109/sti47673.2019.9068092 · Cited by 51
“Tensorflow can be used for all machine learning algorithms where deep learning [12] is specified to neural networks only.”
BackgroundDetection of threat objects in baggage inspection with X-ray images using deep learning
Saavedra, D., Banerjee, S., & Mery, D. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05521-2 · Cited by 56
Shieh, J.-L., Haq, Q. M. U., Haq, M. A., Karam, S., Chondro, P., Gao, D.-Q., & Ruan, S.-J. (2020) · Sensors · doi:10.3390/s20236777 · Cited by 59
Bijalwan, V., Semwal, V. B., Singh, G., & Crespo, R. A. G. (2021) · Expert Systems · doi:10.1111/exsy.12706 · Cited by 52
“The CNN model performs the three important work, that is, sparse interaction, parameter sharing, and equivalent representation and after convolution, there are used pooling and fully connected layers for classification and regression tasks (Zhao, Zheng, et al., 2019; Zhu et al., 2020).”
MethodA Simultaneous Multi-Object Zooming System Using an Ultrafast Pan-Tilt Camera
Hu, S., Shimasaki, K., Jiang, M., Senoo, T., & Ishii, I. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3054425 · Cited by 52
“Recently, deep learning technologies have introduced remarkable advances in multi-object detection [75].”
BackgroundRodríguez, I., Campos, C., & Fdez‐Riverola, F. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06830-w · Cited by 61
“The second group brings together, as pointed out, publications that review the most significant recent DL-based efforts—more specifically, based on CNN—in object detection, introducing and analyzing the detection algorithms and frameworks that have emerged as milestones in the search for higher accuracy, and also cove…”
BackgroundInsect detection from imagery using YOLOv3-based adaptive feature fusion convolution network
Amrani, A., Sohel, F. A., Diepeveen, D., Murray, D., & Jones, M. G. K. (2022) · Australian Journal of Agricultural Research · doi:10.1071/cp21710 · Cited by 56
“Several deep learning models have been developed for tiny object detection (Zhao et al .”
BackgroundLü, S., & Xu, F. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.857513 · Cited by 50
An Improved YOLOv5s Fire Detection Model
Dou, Z., Zhou, H., Liu, Z., Hu, Y., Wang, P., Zhang, J., Wang, Q., Chen, L., Diao, X., & Li, J. (2023) · Fire Technology · doi:10.1007/s10694-023-01492-7 · Cited by 58
“Since traditional object detection uses designed features, the accuracy of object detection cannot meet the actual demand even if the best nonlinear classifier is applied for feature classification [39].”
Axford, D., Sohel, F. A., Vanderklift, M. A., & Hodgson, A. J. (2024) · Ecological Informatics · doi:10.1016/j.ecoinf.2024.102842 · Cited by 50
Bin-Picking for Planar Objects Based on a Deep Learning Network: A Case Study of USB Packs
Le, T.-T., & Lin, C. (2019) · Sensors · doi:10.3390/s19163602 · Cited by 50
“The architecture of the proposed system is presented in Figure”
MethodDeep learning based HEp-2 image classification: A comprehensive review
Rahman, S., Wang, L., Sun, C., & Zhou, L. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101764 · Cited by 55
Li, G., Xie, H., Yan, W., Chang, Y., & Qu, X. (2020) · IEEE Access · doi:10.1109/access.2020.3036620 · Cited by 51
“methods while maintaining high computational speed [11].”
Carranza-García, M., Lara-Benítez, P., García–Gutiérrez, J., & Riquelme, J. C. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.04.001 · Cited by 53
“However, the effectiveness of such generic object detectors when applied to particular applications is still far from optimal [12].”
BackgroundTowards end-to-end car license plate location and recognition in unconstrained scenarios
Qin, S., & Liu, S. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06147-8 · Cited by 53
Jiang, Y. L., & Zhao, C. (2022) · Solar Energy · doi:10.1016/j.solener.2022.04.012 · Cited by 53
A comprehensive review of methods based on deep learning for diabetes-related foot ulcers
Zhang, J., Qiu, Y., Peng, L. H., Zhou, Q., Wang, Z., & Qi, M. (2022) · Frontiers in Endocrinology · doi:10.3389/fendo.2022.945020 · Cited by 59
Aircraft detection in satellite imagery using deep learning-based object detectors
Azam, B., Khan, M. J., Bhatti, F. A., Maud, A. R., Hussain, S. F., Hashmi, A. J., & Khurshid, K. (2022) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2022.104630 · Cited by 52
Obstructive Sleep Apnea Detection Based on Sleep Sounds via Deep Learning
Wang, B., Tang, X., Ai, H., Li, Y., Xu, W., Wang, X., & Han, D. (2022) · Nature and Science of Sleep · doi:10.2147/nss.s373367 · Cited by 49
“As one of the fundamental computer vision problems, object detection has provided valuable information for the semantic understanding of images and videos and has undergone an expansion of its application space in biomedical image processing.(16) The capability of locating targets is of great value not only in identif…”
BackgroundA systematic review of image-level camouflaged object detection with deep learning
Liang, Y., Qin, G., Sun, M., Wang, X., Yan, J., & Zhang, Z. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.127050 · Cited by 58
Computer vision defect detection on unseen backgrounds for manufacturing inspection
Mezher, A. M., & Marble, A. E. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122749 · Cited by 55
Nie, J., Sun, H., Sun, X., Ni, L. Y., & Gao, L. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3339214 · Cited by 55
“Based on whether the regional proposal is utilized or not, deep learning-based object detection algorithms are mainly classified into two types: one-stage object detection and two-stage object detection [3].”
BackgroundAutomatic Food Recognition Using Deep Convolutional Neural Networks with Self-attention Mechanism
Abiyev, R. H., & Adepoju, J. (2024) · Human-Centric Intelligent Systems · doi:10.1007/s44230-023-00057-9 · Cited by 56
“They function especially well with input that has a grid structure, such as images [38].”
Advancements in Artificial Intelligence in Noninvasive Cardiac Imaging: A Comprehensive Review
Tolu-Akinnawo, O. Z., Ezekwueme, F., Omolayo, O. S., Batheja, S., & Awoyemi, T. (2025) · Clinical Cardiology · doi:10.1002/clc.70087 · Cited by 58
“DL is an advanced subset of ML that utilizes specialized neural network architectures known as deep neural networks [14].”
Metadata
- Authors
- Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X.
- Affiliations
- Hefei University of Technology (CN)
- University of Louisiana at Lafayette (US)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2019-11
- Volume
- 30
- Issue
- 11
- Pages
- 3212-3232
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2884367402
- Cited by
- 5,545
- References
- 241
- Citations by year
- 2026: 418 · 2025: 752 · 2024: 866 · 2023: 921 · 2022: 997 · 2021: 887 · 2020: 548 · 2019: 149
- FWCI
- 288.39
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (61672203, 61375047, 91746209)
- National Key Research and Development Program of China (2016YFB1000901)
- Anhui Natural Science Funds for Distinguished Young Scholar (170808J08)
- 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 › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, deep learning, convolutional neural networks, salient object detection, face detection, pedestrian detection, training strategies, optimization functions, image understanding
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.