Skip to main content
SpringerLink
Log in

Dense Face Network: A Dense Face Detector Based on Global Context and Visual Attention Mechanism

  • Research Article
  • Published:
Machine Intelligence Research Aims and scope Submit manuscript

Abstract

Face detection has achieved tremendous strides thanks to convolutional neural networks. However, dense face detection remains an open challenge due to large face scale variation, tiny faces, and serious occlusion. This paper presents a robust, dense face detector using global context and visual attention mechanisms which can significantly improve detection accuracy. Specifically, a global context fusion module with top-down feedback is proposed to improve the ability to identify tiny faces. Moreover, a visual attention mechanism is employed to solve the problem of occlusion. Experimental results on the public face datasets WIDER FACE and FDDB demonstrate the effectiveness of the proposed method.

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

Similar content being viewed by others

References

  1. F. Schroff, D. Kalenichenko, J. Philbin. FaceNet: A unified embedding for face recognition and clustering. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 815–823, 2015. DOI: https://doi.org/10.1109/CVPR.2015.7298682.

    Google Scholar 

  2. F. F. Zhang, T. Z. Zhang, Q. R. Mao, C. S. Xu. Joint pose and expression modeling for facial expression recognition. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 3359–3368, 2018. DOI: https://doi.org/10.1109/CVPR.2018.00354.

    Google Scholar 

  3. K. P. Zhang, Z. P. Zhang, Z. F. Li, Y. Qiao. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499–1503, 2016. DOI: https://doi.org/10.1109/LSP.2016.2603342.

    Article  Google Scholar 

  4. P. Y. Hu, D. Ramanan. Finding tiny faces. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Honolulu, USA, pp. 1522–1530, 2017. DOI: https://doi.org/10.1109/CVPR.2017.166.

    Google Scholar 

  5. M. Najibi, P. Samangouei, R. Chellappa, L. S. Davis. SSH: Single stage headless face detector. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Venice, Italy, pp. 4885–4894, 2017. DOI: https://doi.org/10.1109/ICCV.2017.522.

    Google Scholar 

  6. J. K. Deng, J. Guo, Y. X. Zhou, J. K. Yu, I. Kotsia, S. Zafeiriou. RetinaFace: Single-stage dense face localisation in the wild. [Online], Available: https://arxiv.org/abs/1905.00641, 2019.

  7. T. Y. Lin, P. Goyal, R. Girshick, K. M. He, P. Dollár. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 318–327, 2020. DOI: https://doi.org/10.1109/TPAMI.2018.2858826.

    Article  Google Scholar 

  8. V. Jain, E. Learned-Miller. FDDB: A Benchmark for Face Detection in Unconstrained Settings, Technical Report UM-CS-2010–009, University of Massachusetts, USA, 2010.

    Google Scholar 

  9. S. Yang, P. Luo, C. C. Loy, X. O. Tang. WIDER FACE: A face detection benchmark. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 5525–5533, 2016. DOI: https://doi.org/10.1109/CV-PR.2016.596.

    Google Scholar 

  10. C. C. Zhu, Y. T. Zheng, K. Luu, M. Savvides. CMS-RCNN: Contextual multi-scale region-based CNN for unconstrained face detection. Deep Learning for Biometrics, B. Bhanu, A. Kumar, Eds., Cham, Germany: Springer, pp. 57–79, 2017. DOI: https://doi.org/10.1007/978-3-319-61657-5_3.

    Chapter  Google Scholar 

  11. S. Q. Ren, K. M. He, R. Girshick, J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 91–99, 2015. DOI: https://doi.org/10.5555/2969239.2969250.

  12. T. Xu, D. K. Du, Z. Q. He, J. T. Liu. PyramidBox: A context-assisted single shot face detector. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 812–828, 2018. DOI: https://doi.org/10.1007/978-3-030-01240-3_49.

    Google Scholar 

  13. S. F. Zhang, X. Y. Zhu, Z. Lei, H. L. Shi, X. B. Wang, S. Z. Li. S.3FD: Single shot scale-invariant face detector. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Venice, Italy, pp. 192–201, 2017. DOI: https://doi.org/10.1109/ICCV.2017.30.

    Google Scholar 

  14. M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu. Spatial transformer networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 2017–2025, 2015. DOI: https://doi.org/10.5555/2969442.2969465.

  15. J. Hu, L. Shen, S. Albanie, G. Sun, E. H. Wu. Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 8, pp. 2011–2023, 2020. DOI: https://doi.org/10.1109/TPAMI.2019.2913372.

    Article  Google Scholar 

  16. S. Woo, J. Park, J. Y. Lee, I. S. Kweon. CBAM: Convolutional block attention module. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 3–19, 2018. DOI: https://doi.org/10.1007/978-3-030-01234-21.

    Google Scholar 

  17. J. F. Wang, Y. Yuan, G. Yu. Face attention network: An effective face detector for the occluded faces. [Online], Available: https://arxiv.org/abs/1711.07246, 2017.

  18. A. G. Howard, M. L. Zhu, B. Chen, D. Kalenichenko, W. J. Wang, T. Weyand, M. Andreetto, H. Adam. MobileNets: Efficient convolutional neural networks for mobile vision applications. [Online], Available: https://arxiv.org/abs/1704.04861, 2017.

  19. K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Las Vegas, USA, pp. 770–778, 2016. DOI: https://doi.org/10.1109/CVPR.2016.90.

    Google Scholar 

  20. S. S. Farfade, M. J. Saberian, L. J. Li. Multi-view face detection using deep convolutional neural networks. In Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, ACM, Shanghai, China, pp. 643–650, 2015. DOI: https://doi.org/10.1145/2671188.2749408.

    Google Scholar 

  21. H. X. Li, Z. Lin, X. H. Shen, J. Brandt, G. Hua. A convolutional neural network cascade for face detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Boston, USA, pp. 5325–5334, 2015. DOI: https://doi.org/10.1109/CVPR.2015.7299170.

    Google Scholar 

  22. R. Girshick. Fast R-CNN. In Proceedings of IEEE International Conference on Computer Vision, IEEE, Santiago, Chile, pp. 1440–1448, 2015. DOI: https://doi.org/10.1109/ICCV.2015.169.

    Google Scholar 

  23. R. Ranjan, V. M. Patel, R. Chellappa. A deep pyramid deformable part model for face detection. In Proceedings of the 7th IEEE International Conference on Biometrics Theory, Applications and Systems, IEEE, Arlington, USA, pp. 1–8, 2015. DOI: https://doi.org/10.1109/BTAS.2015.7358755.

    Google Scholar 

  24. J. H. Yu, Y. N. Jiang, Z. Y. Wang, Z. M. Cao, T. Huang. UnitBox: An advanced object detection network. In Proceedings of the 24th ACM International Conference on Multimedia, ACM, Amsterdam, The Netherlands, pp. 516–520, 2016. DOI: https://doi.org/10.1145/2964284.2967274.

    Google Scholar 

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (No. 61973009).

Author information

Authors and Affiliations

  1. Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China

    Lin Song, Jin-Fu Yang, Qing-Zhen Shang & Ming-Ai Li

  2. Beijing Key Laboratory of Computational Intelligence and Intelligent Systems, Beijing, 100124, China

    Jin-Fu Yang

Authors
  1. Lin Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jin-Fu Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qing-Zhen Shang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ming-Ai Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lin Song.

Additional information

Colored figures are available in the online version at https://link.springer.com/journal/11633

Lin Song received the B.Sc. degree in measurement and control technology and instrumentation from YanTai University, China in 2019. She is now a master student with Department of Control Science and Engineering, Beijing University of Technology, China.

Her research interests include deep learning and computer vision.

Jin-Fu Yang received the Ph.D. degree in pattern recognition and intelligent systems from National Laboratory of Pattern Recognition, Chinese Academy of Sciences, China in 2006. He is now a professor with Faculty of Information Technology and Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, China.

His research interests include pattern recognition, computer vision and robot navigation.

Qing-Zhen Shang received the M. Eng. degree in mathematics from Hebei University, China in 2017. She is a Ph.D. degree candidate at Department of Control Science and Engineering, Beijing University of Technology, China.

Her research interests include deep learning and computer vision.

Ming-Ai Li received the Ph.D. degree from Beijing University of Technology, China in 2006. She is now a professor with Faculty of Information Technology and Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, China.

Her research interests include brain-computer interface, intelligent control, pattern recognition and implementation of autonomous learning control technology for flexible two-wheeled upstanding robots.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Song, L., Yang, JF., Shang, QZ. et al. Dense Face Network: A Dense Face Detector Based on Global Context and Visual Attention Mechanism. Mach. Intell. Res. 19, 247–256 (2022). https://doi.org/10.1007/s11633-022-1327-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11633-022-1327-2

Keywords

Search

Navigation