Skip to main content
SpringerLink
Log in

Saliency-based YOLO for single target detection

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

At present, You only look once (YOLO) is the fastest real-time object detection system based on a unified deep neural network. During training, YOLO divides the input image to \(S \times S \) gird cells and the only one grid cell that contains the center of an object, takes charge of detecting that object. It is not sure that the cell corresponding to the center of the object is the best choice to detect the object. In this paper, inspired by the visual saliency mechanism we introduce the saliency map to YOLO to develop YOLO3-SM method, where saliency map selects the grid cell containing the most salient part of the object to detect the object. The experimental results on two data sets show that the prediction box of YOLO3-SM obtains the lager IOU value, which demonstrates that compared with YOLO3 , the YOLO3-SM selects the cell that is more suitable to detect the object . In addition, YOLO3-SM gets the highest mAP that the other three state-of-the-art object detection methods on the two data sets, which shows that introducing the saliency map to YOLO can improve the detection performance.

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

Similar content being viewed by others

Notes

  1. https://github.com/experiencor/raccoon_dataset.

  2. https://v.youku.com/v_show/id_XMzc5NTQwNjEyNA==.html?spm=a2h3j.8428770.3416059.1.

  3. https://github.com/experiencor/kangaroo.

  4. https://v.youku.com/v_show/id_XNDU2NzMxNjY2NA==.html.

References

  1. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer vision and pattern recognition (CVPR), pp 580–587

  2. Girshick R (2015) Fast R-CNN. In:: Computer vision and pattern recognition (CVPR), pp 1440–1448

  3. Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems (NIPS), pp 91–99

  4. Redmon J, Divvala S, Girshick R et al (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

  5. Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21–37

  6. He K, Gkioxari G, Dollár P, Girshick R (2017) Mask R-CNN. In: Computer vision (ICCV), pp 2980–2988

  7. Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263–7271

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

  9. Borji Ali, Itti L (2013) State-of-the-art in visual attention modeling. IEEE Trans Pattern Anal Mach Intell 35(1):185–207

    Article  Google Scholar 

  10. Rutishauser U et al (2004) Is bottom-up attention useful for object recognition? In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition, vol 2, p II

  11. Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3586–3593

  12. Wu R, Yu Y, Wang W (2013) Scale: supervised and cascaded Laplacian eigenmaps for visual object recognition based on nearest neighbors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 867–874

  13. Welleck S, Mao J, Cho K et al (2017) Saliency-based sequential image attention with multiset prediction. In: Advances in neural information processing systems, pp 5173–5183

  14. Zagoruyko S, Komodakis N (2016) Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. arXiv:1612.03928

Download references

Acknowledgements

This work is supported by the National Key Research and Development Program of China: 2018YFC0809001, the Natural Science Foundation of China: 61572393, 61877049, 11671317, 12001428.

Author information

Authors and Affiliations

  1. School of Mathematics, Northwest University, Xi’an, 710127, China

    Jun-ying Hu

  2. School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, 710049, China

    Jun-ying Hu & Jiang-she Zhang

  3. Department of Electrical Engineering, University of Washington, Seattle, 98195, USA

    C.-J. Richard Shi

Authors
  1. Jun-ying Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C.-J. Richard Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jiang-she Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiang-she Zhang.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, Jy., Shi, CJ.R. & Zhang, Js. Saliency-based YOLO for single target detection. Knowl Inf Syst 63, 717–732 (2021). https://doi.org/10.1007/s10115-020-01538-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-020-01538-0

Keywords

Search

Navigation