Skip to main content
SpringerLink
Log in

Improved YOLOv5 Network with Attention and Context for Small Object Detection

  • Conference paper
  • First Online:
Book cover Intelligent Computing Methodologies (ICIC 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13395))

Included in the following conference series:

Abstract

Object detection is one of the most important and challenging branches in computer vision. Although impressive progress have been achieved on large or medium scale objects, detecting small objects from images is still difficult due to the limited image size and feature information. To deal with the small object detection problem, we explore how the popular YOLOv5 object detector can be modified to improve its performance on detecting small objects. To achieve this, we integrate Coordinate Attention (CA) and Context Feature Enhancement Module (CFEM) in YOLOv5 network. Coordinate Attention is based on attention mechanism and it embeds positional information into channel attention, which enables deep neural network to augment the representations of the objects of interest. Context Feature Enhancement Module explores rich context information from multiple receptive fields and only contains several additional layers. Extensive experimental results on the VisDrone-Detection dataset demonstrate that our approach can improve the performance of the proposed method for small object detection.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 229.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 299.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  2. Wu, Q., Shen, C., Wang, P., Dick, A., Van Den Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1367–1381 (2017)

    Article  Google Scholar 

  3. Zhao, Z.Q., Gao, J., Glotin, H., Wu, X.: A matrix modular neural network based on task decomposition with subspace division by adaptive affinity propagation clustering. Appl. Math. Model. 34(12), 3884–3895 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  4. Zhao, Z., Wu, X., Lu, C., Glotin, H., Gao, J.: Optimizing widths with pso for center selection of gaussian radial basis function networks. Sci. China Inf. Sci. 57(5), 1–17 (2014)

    Article  Google Scholar 

  5. Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)

    Google Scholar 

  6. Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)

    Google Scholar 

  7. Dai, J., Li, Y., He, K., Sun, J.: R-fcn: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)

    Google Scholar 

  8. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    Google Scholar 

  9. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

    Google Scholar 

  10. Liu, W., et al.: Ssd: Single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.)  ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2

    Chapter  Google Scholar 

  11. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  12. Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1222–1230 (2017)

    Google Scholar 

  13. Bell, S., Zitnick, C.L., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2874–2883 (2016)

    Google Scholar 

  14. Shrivastava, A., Sukthankar, R., Malik, J., Gupta, A.: Beyond skip connections: top-down modulation for object detection. arXiv preprint arXiv:1612.06851 (2016)

  15. Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659

  16. Chen, C., Liu, M.-Y., Tuzel, O., Xiao, J.: R-cnn for small object detection. In: Lai, S.-H., Lepetit, V., Nishino, Ko., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10115, pp. 214–230. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54193-8_14

    Chapter  Google Scholar 

  17. Ultralytics. YOLOv5 (2020). https://github.com/ultralytics/yolov5

  18. Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE cConference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)

    Google Scholar 

  19. Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vision 104(2), 154–171 (2013)

    Article  Google Scholar 

  20. Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154–6162 (2018)

    Google Scholar 

  21. Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6569–6578 (2019)

    Google Scholar 

  22. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)

    Google Scholar 

  23. Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.)  ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1

    Chapter  Google Scholar 

  24. Cao, J., Chen, Q., Guo, J., Shi, R.: Attention-guided context feature pyramid network for object detection. arXiv preprint arXiv:2005.11475 (2020)

  25. Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)

    Google Scholar 

  26. Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systemsm vol. 30 (2017)

    Google Scholar 

  27. Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520–527 (2007)

    Article  Google Scholar 

  28. Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)

  29. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 (2014)

  30. Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)

  31. Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13713–13722 (2021)

    Google Scholar 

  32. Zhu, P., Wen, L., Bian, X., Ling, H., Hu, Q.: Vision meets drones: a challenge. arXiv preprint arXiv:1804.07437 (2018)

  33. Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

  34. Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)

Download references

Acknowlegment

This work was supported in part by the National Natural Science Foundation of China under Grant 61976079, in part by Guangxi Key Research and Development Program under Grant 2021AB20147, and in part by Anhui Key Research and Development Pro-gram under Grant 202004a05020039.

Author information

Authors and Affiliations

  1. College of Computer and Information, Hefei University of Technology, Hefei, Anhui, China

    Tian-Yu Zhang, Zhong-Qiu Zhao & Wei-Dong Tian

  2. Intelligent Manufacturing Institute of HFUT, Hefei, China

    Tian-Yu Zhang, Zhong-Qiu Zhao & Wei-Dong Tian

  3. Anhui Fiber Inspection Bureau, Hefei, China

    Jun Li & Jie Chai

  4. Guangxi Academy of Science, Guangzhou, China

    Zhong-Qiu Zhao

Authors
  1. Tian-Yu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jie Chai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhong-Qiu Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wei-Dong Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhong-Qiu Zhao .

Editor information

Editors and Affiliations

  1. Tongji University, Shanghai, China

    De-Shuang Huang

  2. University of Ulsan, Ulsan, Korea (Republic of)

    Kang-Hyun Jo

  3. Xi’an Polytechnic University, Xi’an, China

    Junfeng Jing

  4. The University of Wollongong, North Wollongong, NSW, Australia

    Prashan Premaratne

  5. Polytecnic of Bari, Bari, Italy

    Vitoantonio Bevilacqua

  6. Liverpool John Moores University, Liverpool, UK

    Abir Hussain

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, TY., Li, J., Chai, J., Zhao, ZQ., Tian, WD. (2022). Improved YOLOv5 Network with Attention and Context for Small Object Detection. In: Huang, DS., Jo, KH., Jing, J., Premaratne, P., Bevilacqua, V., Hussain, A. (eds) Intelligent Computing Methodologies. ICIC 2022. Lecture Notes in Computer Science(), vol 13395. Springer, Cham. https://doi.org/10.1007/978-3-031-13832-4_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-13832-4_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-13831-7

  • Online ISBN: 978-3-031-13832-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation