Skip to main content
SpringerLink
Log in

CALYOLOv4: lightweight YOLOv4 target detection based on coordinated attention

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

The current deep learning-based target detection algorithm YOLOv4 has a large number of redundant convolutional computations, resulting in much consumption of memory and computational resources, making it difficult to apply on mobile devices with limited computational power and storage resources. We propose a lightweight YOLOv4 (CALYOLOv4) target detection algorithm based on coordinated attention to solve this problem. First, we use MobileNetv2CA with a coordinated attention mechanism instead of CSPDarknet53 as the backbone feature extraction network to reduce network parameters and improve network attention. Second, we use depthwise separable convolutions and mixed depth convolutions (MixConv) to replace the standard convolution in the network, further reducing the parameters and computation of the network. Finally, we choose a better-weighted bidirectional feature pyramid (BiFPN) to replace PANet as the feature fusion network to fully fuse features between different scales. The test results on the PASCAL VOC and MS COCO datasets show that, compared with the YOLOv4 algorithm, our proposed CALYOLOv4 algorithm has 89.1% fewer model total parameters and is 1.71 times faster, reaching 65 frames per second on NVIDIA GeForce RTX 3060, with 81.0% and 29.6% detection accuracy, respectively, achieving the best balance of accuracy and speed. The feasibility and effectiveness of the proposed algorithm are fully demonstrated.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Availability of data and materials

Research data are not shared.

References

  1. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  2. Xu Q, Wang G, Li Y, Shi L, Li Y (2021) A comprehensive swarming intelligent method for optimizing deep learning-based object detection by unmanned ground vehicles. Plos one 16(5):e0251339

    Article  Google Scholar 

  3. Tian Y, Su D, Lauria S, Liu X (2022) Recent advances on loss functions in deep learning for computer vision. Neurocomputing

  4. Bouraoui A, Jamoussi S, Hamadou AB (2022) A comprehensive review of deep learning for natural language processing. Int J Data Min Modell Manag 14(2):149–182

    Google Scholar 

  5. Sun X, Yang D, Li X, Zhang T, Meng Y, Han Q, Wang G, Hovy E, Li J (2021) Interpreting deep learning models in natural language processing: a review. arXiv preprint arXiv:2110.10470

  6. Vilaça L, Yu Y, Viana P (2022) Recent advances and challenges in deep audio-visual correlation learning. arXiv preprint arXiv:2202.13673

  7. Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans Patt Analy Mach Intell 39(6):1137–1149

    Article  Google Scholar 

  8. Bell S, Zitnick CL, Bala K, Girshick R (2016) 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

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

  10. Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934

  11. Deng W, Xu J, Gao XZ, Zhao H (2020) An enhanced msiqde algorithm with novel multiple strategies for global optimization problems. IEEE Trans Syst, Man, Cybern Syst 52(3):1578–1587

    Article  Google Scholar 

  12. Zhao H, Yang X, Chen B, Chen H, Deng W (2022) Bearing fault diagnosis using transfer learning and optimized deep belief network. Measur Sci Technol 33(6):065009

    Article  Google Scholar 

  13. Deng W, Xu J, Song Y, Zhao H (2021) Differential evolution algorithm with wavelet basis function and optimal mutation strategy for complex optimization problem. Appl Soft Comput 100:106724

    Article  Google Scholar 

  14. Zhao H, Zhang P, Zhang R, Yao R, Deng W (2022) A novel performance trend prediction approach using enbls with gwo. Measur Sci Technol 34(2):025018

    Article  Google Scholar 

  15. Sain SR (1996) The nature of statistical learning theory

  16. Rosenberg C, Hebert M, Schneiderman H (2005) Semi-supervised self-training of object detection models

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

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

  19. Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. Adv Neural Inf Process Syst 29

  20. He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Patt Analy Mach Intell 37(9):1904–1916

    Article  Google Scholar 

  21. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556

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

  23. Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7263–7271

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

  25. Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, et al. (2022) Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976

  26. Wang CY, Bochkovskiy A, Liao HYM (2022) Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696

  27. Xu S, Wang X, Lv W, Chang Q, Cui C, Deng K, Wang G, Dang Q, Wei S, Du Y, et al. (2022) Pp-yoloe: An evolved version of yolo. arXiv preprint arXiv:2203.16250

  28. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: European Conference on Computer Vision, Springer, pp 21–37

  29. Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659

  30. Li Z, Zhou F (2017) Fssd: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960

  31. Zheng W, Tang W, Jiang L, Fu CW (2021) Se-ssd: Self-ensembling single-stage object detector from point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 14494–14503

  32. Law H, Deng J (2018) Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 734–750

  33. Tian Z, Shen C, Chen H, He T (2019) Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9627–9636

  34. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861

  35. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4510–4520

  36. Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6848–6856

  37. Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 116–131

  38. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1–9

  39. Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, PMLR, pp 448–456

  40. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2818–2826

  41. Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI Conference on Artificial Intelligence

  42. Xie S, Girshick R, Dollár P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1492–1500

  43. Zhuang Z, Tan M, Zhuang B, Liu J, Guo Y, Wu Q, Huang J, Zhu J (2018) Discrimination-aware channel pruning for deep neural networks. Advances in neural information processing systems 31

  44. He Y, Zhang X, Sun J (2017) Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1389–1397

  45. Yang C, Liu H (2022) Channel pruning based on convolutional neural network sensitivity. Neurocomputing 507:97–106

    Article  Google Scholar 

  46. Liu Y, Guo Y, Guo J, Jiang L, Chen J (2021) Conditional automated channel pruning for deep neural networks. IEEE Signal Process Lett 28:1275–1279

    Article  Google Scholar 

  47. Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) Xnor-net: Imagenet classification using binary convolutional neural networks. In: European Conference on Computer Vision, Springer, pp 525–542

  48. Li F, Zhang B, Liu B (2016) Ternary weight networks. arXiv preprint arXiv:1605.04711

  49. Zhu C, Han S, Mao H, Dally WJ (2016) Trained ternary quantization. arXiv preprint arXiv:1612.01064

  50. Tan M, Pang R, Le QV (2020) Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 10781–10790

  51. Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8759–8768

  52. Wang CY, Liao HYM, Wu YH, Chen PY, Hsieh JW, Yeh IH (2020) Cspnet: A new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp 390–391

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

  54. Tan M, Le QV (2019) Mixconv: Mixed depthwise convolutional kernels. arXiv preprint arXiv:1907.09595

  55. Li L, Li B, Zhou H (2022) Lightweight multi-scale network for small object detection. PeerJ Comput Sci 8:e1145

    Article  Google Scholar 

  56. Ding P, Qian H, Chu S (2022) Slimyolov4: Lightweight object detector based on yolov4. J Real-Time Image Process 19(3):487–498

    Article  Google Scholar 

  57. Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338

    Article  Google Scholar 

  58. Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European Conference on Computer Vision, Springer, pp 740–755

Download references

Funding

This work was supported by Key-Area Research and Development Program of Guangdong Province under Grant (Funding No.: 2020B0909020001) and National Natural Science Foundation of China (Funding No.: 61573113).

Author information

Authors and Affiliations

  1. College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China

    Huilin Wang, Huaming Qian, Shuai Feng & Shuya Yan

Authors
  1. Huilin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Huaming Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shuai Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shuya Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

HW wrote the main manuscript text. SF, SY Modify syntax. All authors reviewed the manuscript.

Corresponding author

Correspondence to Huaming Qian.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicts of interest.

Ethical approval

this declaration is not applicable

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, H., Qian, H., Feng, S. et al. CALYOLOv4: lightweight YOLOv4 target detection based on coordinated attention. J Supercomput 79, 18947–18969 (2023). https://doi.org/10.1007/s11227-023-05380-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-023-05380-3

Keywords

Search

Navigation