Mini-YOLOv3: Real-Time Object Detector for Embedded Applications
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Real-time scene parsing through object detection running on an embedded device is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, we redesign a lightweight network without notably reducing detection accuracy. Based on the Darknet-53, we use depth separable convolutions and pointwise group convolutions to reduce the parameter size of the network. A feature extraction backbone network with a parameter size of only 16 percent of darknet-53 is constructed. Meanwhile, in order to compensate for the degradation of accuracy, we have added a Multi-Scale Feature Pyramid Network based on a simple U-shaped structure to improve the performance of multi-scale object detection, which called it Mini-YOLOv3. It has smaller model size and fewer trainable parameters and floating point operations (FLOPs) in comparison of YOLOv3. We evaluate Mini-YOLOv3 on MS-COCO benchmark dataset; The parameter size of Mini-YOLOv3 is only 23% of YOLOv3 and achieves comparable detection accuracy as YOLOv3 but only requires 1/2 detect time, Specifically, Mini-YOLOv3 achieves mAP-50 of 52.1 at speed of 67 fps.
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.
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
ImageNet 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
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
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
You 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
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Histograms 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
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · cited 1×
“6 105ms RetinaNet400[42] ResNet-101 31.”
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 2×
“First, we define the unit of the network: We changed the standard convolution to depthwise separable convolutions according to Google ‘‘Xception’’ [33].”
MethodYOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Cascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370
The Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · cited 2×
“Because of the growth of computing power and the dedicated deep learning chips and the availability of large-scale labelled samples (e.g., ImageNet [10], [11], PASCAL VOC [12] and MS-COCO [13]), Convolutional Neural Network(CNN) has been extensively studied due to its fast, scalable and end to-end learning framework.”
BackgroundSqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201 · cited 3×
“For example, SqueezeNet [28], MobileNet [29], ShffuleNet [30], etc.”
MethodInfluentialObject Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545 · cited 1×
“It is the basic premise for advanced visual tasks such as Video Content Recognition (VCR) and Image Understanding (IU) [3].”
BackgroundCornerNet: Detecting Objects as Paired Keypoints
Law, H., & Deng, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_45 · Cited by 3,852
Single-Shot Refinement Neural Network for Object Detection
Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S. Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00442 · Cited by 1,678
DSSD : Deconvolutional Single Shot Detector
Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017) · arXiv · doi:10.48550/arxiv.1701.06659 · Cited by 1,624 · cited 2×
“Recently, some fast single-stage object detectors have been proposed, such as SSD [20], DSSD [21], YOLO series models [22]–[24], RetinaNet [25] ,etc.”
MethodInfluentialYOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
Huang, R., Pedoeem, J., & Chen, C. (2018) · 2018 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata.2018.8621865 · Cited by 622
Research works printed but not linked: 17
- dai, 2016, R-FCN: Object detection via region-based fully convolutional networks, Proc Adv Neural Inf Process Syst, 379
- 10.1109/ICPR.2006.479 · DOI · Paper page
- 10.1109/50.90937 · DOI · Paper page
- iandola, 2014, DenseNet: Implementing efficient convNet descriptor pyramids, Arxiv 1404 1869
- 10.1109/CVPR.2018.00109 · DOI · Paper page
- lin, 2014, Microsoft COCO: Common objects in context, Proc Eur Conf Comput Vis, 740
- 10.1109/CVPR.2014.81 · DOI · Paper page
- fridman, 2017, MIT advanced vehicle technology study: Large-scale naturalistic driving study of driver behavior and interaction with automation, arXiv 1711 06976
- 10.1109/SITIS.2016.17 · DOI
- iandola, 2016, SqueezeNet: AlexNet-level accuracy with $50\times$ fewer parameters and < 0.5 MB model size, arXiv 1602 07360
- 10.1109/CVPR.2001.990517 · DOI · Paper page
- wong, 2018, Tiny SSD: A tiny single-shot detection deep convolutional neural network for real-time embedded object detection, ArXiv 1802 06488
- 10.1006/cviu.1999.0830 · DOI · Paper page
- freund, 1996, Experiments with a new boosting algorithm, Proc 13th Int Conf Mach Learn, 148
- 10.1007/978-3-319-07488-7_8 · DOI
- 10.1109/CVPR.2008.4587597 · DOI · Paper page
- 10.1109/CVPR.2018.00719 · DOI · Paper page
Cited by
Object detection using YOLO: challenges, architectural successors, datasets and applications
Diwan, T., Anirudh, G., & Tembhurne, J. V. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13644-y · Cited by 1,549
“[47] YOLO v3 Object detection in real-rime for embedded system • Darknet-53 applied as a feature extractor • Pyramid network to enhance the performance of multi-scale object detection • mAP-50 of 52.”
BackgroundYOLO v3-Tiny: Object Detection and Recognition using one stage improved model
Adarsh, P., Rathi, P., & Kumar, M. (2020) · 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs48705.2020.9074315 · Cited by 545
Yeh, C.-H., Lin, C.-H., Kang, L.-W., Huang, C.-H., Lin, M.-H., Chang, C.-Y., & Wang, C.-C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3072414 · Cited by 260
A comprehensive survey of deep learning-based lightweight object detection models for edge devices
Mittal, P. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10877-1 · Cited by 244
Real-time object detection method based on improved YOLOv4-tiny
Jiang, Z., Zhao, L., Li, S., & Jia, Y. (2020) · arXiv · doi:10.48550/arxiv.2011.04244 · Cited by 171
Metadata
- Authors
- Mao, Q.-C., Sun, H.-M., Liu, Y.-B., & Jia, R.-S.
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 133529-133538
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2973696262
- Cited by
- 224
- References
- 27
- FWCI
- 13.63
- Type
- journal article
- Language
- en
- Open access
- gold
- Funders
- Natural Science Foundation of Shandong Province (ZR2018MEE008)
- Key Research and Development Program of Shandong Province, China (2017GSF20115)
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.