skip to main content
10.1145/3573942.3574025acmotherconferencesArticle/Chapter ViewAbstractPublication PagesaiprConference Proceedingsconference-collections
research-article

Model Lightweight Method for Object Detection

Published: 16 May 2023 Publication History

Abstract

The rapid development of object detection technology benefits from the development of convolutional neural network. However, the convolution neural network needs a deep enough convolution layer to obtain more abundant image feature information and the complexity of the network itself, which makes the object detection network have some limitations, such as large amount of model parameters, unable to achieve real-time detection speed, high requirements for computing resources and so on. Based on the efficientdet model and the LD-BiFPN network, this paper explores the difference between the adaptive fusion method and the fast fusion method, and designs a feature layer pruning method of the weight matrix according to the weight matrix representing the importance of the feature layer in the fast fusion method, to prune the LD-BiFPN network to reduce the network parameters. Then convolution filter pruning method is introduced to prune the classification and regression network of the model, so as to reduce the parameters of the network and improve the detection speed. Experiments show that the designed lightweight method can reduce the parameters of the model and improve the detection speed on the premise of ensuring the detection accuracy.t

References

[1]
Iandola F N, Han S, Moskewicz M W, SqueezeNet: alexnet-level accuracy with 50x fewer parameters and < 0.5 MB model size [J]. arXiv preprint arXiv: 1602.07360, 2016.
[2]
Howard A G, Zhu M, Chen B, Mobilenets: efficient convolutional neural networks for mobile vision applications [J]. arXiv preprint arXiv: 1704.04861, 2017.
[3]
Chollet F. Xception: Deep learning with depthwise separable convolutions[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.
[4]
Zhang X, Zhou X, Lin M, Shufflenet: an extremely efficient convolutional neural network for mobile devices [C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2018: 6848-6856.
[5]
Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks [C]. International conference on machine learning, PMLR, 2019: 6105-6114.
[6]
Han S, Mao H, Dally W J. Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding [J]. arXiv preprint arXiv, 1510.00149, 2015.
[7]
Wen W, Wu C, Wang Y, Learning structured sparsity in deep neural networks [J]. arXiv preprint arXiv: 1608.03665, 2016.
[8]
Rao Y, Lu J, Lin J, Runtime network routing for efficient image classification [J]. IEEE transactions on Pattern Analysis and Machine Intelligence, 2018, 41(10): 2291-2304.
[9]
He Y, Zhang X, Sun J. Channel pruning for accelerating very deep neural networks [C]. Proceedings of the IEEE International Conference on Computer Vision, 2017: 1389-1397.
[10]
Yu R, Li A, Chen C F, Nisp: pruning networks using neuron importance score propagation [C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2018: 9194-9203.
[11]
He Y, Liu P, Wang Z, Filter pruning via geometric median for deep convolutional neural networks acceleration [C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2019: 4340-4349.
[12]
Lin T Y, Dollár P, Girshick R, Feature pyramid networks for object detection [C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125.
[13]
Liu S, Qi L, Qin H, Path aggregation network for instance segmentation[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8759-8768.
[14]
Kim S W, Kook H K, Sun J Y, Parallel feature pyramid network for object detection[C]. Proceedings of the European Conference on Computer Vision. 2018: 234-250.
[15]
Zhao Q, Sheng T, Wang Y, M2det: A single-shot object detector based on multi-level feature pyramid network. Proceedings of the AAAI conference on artificial intelligence. 2019, 33(01): 9259-9266.
[16]
Ghiasi G, Lin T Y, Le Q V. Nas-fpn: Learning scalable feature pyramid architecture for object detection[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 7036-7045.
[17]
Guo C, Fan B, Zhang Q, Augfpn: Improving multi-scale feature learning for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 12595-12604.
[18]
Wang J, Tong Q J, He C. A longitudinal dense feature pyramid network for object detection [C]. International Conference on Artificial Intelligence and Pattern Recognition, 2021: 518-523.
[19]
Tan M, Pang R, Le Q V. Efficientdet: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10781-10790.
[20]
Liu S, Huang D, Wang Y. Learning spatial fusion for single-shot object detection[EB]. arXiv preprint arXiv:1911.09516, 2019.
[21]
Lin T Y, Maire M, Belongie S, Microsoft coco: common objects in context [C]. European Conference on Computer Vision. Springer, Cham, 2014: 740-755.

Cited By

View all
  • (2024)Toward Oriented Fisheye Object Detection: Dataset and BaselineACM Transactions on Multimedia Computing, Communications, and Applications10.1145/370264021:1(1-19)Online publication date: 2-Nov-2024

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition
September 2022
1221 pages
ISBN:9781450396899
DOI:10.1145/3573942
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 May 2023

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Convolutional neural network
  2. Fast fusion method
  3. Network pruning
  4. Object detection

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

AIPR 2022

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)12
  • Downloads (Last 6 weeks)0
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Toward Oriented Fisheye Object Detection: Dataset and BaselineACM Transactions on Multimedia Computing, Communications, and Applications10.1145/370264021:1(1-19)Online publication date: 2-Nov-2024

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media