Skip to main content
SpringerLink
Log in

DFL-Net: Effective Object Detection via Distinguishable Feature Learning

  • Conference paper
  • First Online:
Database and Expert Systems Applications (DEXA 2021)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 12924))

Included in the following conference series:

Abstract

The one-stage anchor-based approach has been an efficient and effective approach for detecting objects from massive image data. However, it neglects many distinguishable features of objects, which will lower the accuracy of object detection. In this paper, we propose a new object detection approach that improves existing one-stage anchor-based methods via a Distinguishable Feature Learning Network (DFL-Net). DFL-Net integrates distinguishable features into the learning process to improve the accuracy of object detection. Notably, we implement DFL-Net by a full-scale fusion module and an attention-guided module. In the full-scale fusion module, we first learn the distinguishable features at each scale (layer) and then fuse them in all layers to generate full-scale features. This differs from prior work that only considered one or limited scales and limited features. In the attention-guided module, we extract more distinguishable features based on some positive or negative samples. We conduct extensive experiments on two public datasets, including PASCAL VOC and COCO, to compare the proposed DFL-Net with several one-stage approaches. The results show that DFL-Net achieves a high mAP of 83.1% and outperforms all its competitors. We also compare DFL-Net with three two-stage algorithms, and the results also suggest the superiority of DFL-Net.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)

    Google Scholar 

  2. Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS, pp. 379–387 (2016)

    Google Scholar 

  3. 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 

  4. Fu, C.Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)

  5. Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2980–2988 (2017)

    Google Scholar 

  6. Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: CVPR, pp. 4203–4212 (2018)

    Google Scholar 

  7. Li, S., Yang, L., Huang, J., Hua, X.S., Zhang, L.: Dynamic anchor feature selection for single-shot object detection. In: ICCV, pp. 6609–6618 (2019)

    Google Scholar 

  8. Law, H., Deng, J.: Cornernet: detecting objects as paired keypoints. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 765–781. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_45

    Chapter  Google Scholar 

  9. Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)

  10. Kong, T., Sun, F., Liu, H., Jiang, Y., Shi, J.: FoveaBox: beyond anchor-based object detector. arXiv preprint arXiv:1904.03797 (2019)

  11. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125 (2017)

    Google Scholar 

  12. 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 

  13. Everingham, M., Van, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2007 (2007). http://host.robots.ox.ac.uk/pascal/VOC/voc2007

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

  15. Yi, J., Wu, P., Metaxas, D.N.: ASSD: attentive single shot multibox detector. In: CVIU, vol. 189 (2019)

    Google Scholar 

  16. Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In CVPR, pp. 6154–6162 (2018)

    Google Scholar 

  17. Duan, K. Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: ICCV, pp. 6569–6578 (2019)

    Google Scholar 

  18. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image detection. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  19. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  20. Zhu Y., Zhao C., Wang J., Zhao X., Wu Y., Lu H.: CoupleNet: coupling global structure with local parts for object detection. In: ICCV, pp. 4126–4134 (2017)

    Google Scholar 

  21. Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. In: CoRR, abs/1804.02767 (2018)

    Google Scholar 

  22. Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In CVPR, pp. 761–769 (2016)

    Google Scholar 

  23. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779–788 (2016)

    Google Scholar 

  24. Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR, pp. 6517–6525 (2017)

    Google Scholar 

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

  26. Yang, X., Wan, S., Jin, P., Zou, C., Li, X.: MHEF-TripNet: mixed triplet loss with hard example feedback network for image retrieval. In: Zhao, Y., Barnes, N., Chen, B., Westermann, R., Kong, X., Lin, C. (eds.) ICIG 2019. LNCS, vol. 11903, pp. 35–46. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34113-8_4

    Chapter  Google Scholar 

  27. Sun, Z., Cao, S., Yang, Y., Kris, K.: Rethinking transformer-based set prediction for object detection. arXiv preprint arXiv:2011.10881 (2020)

  28. Tian, Q., Wan, S., Jin, P., Xu, J., Zou, C., Li, X.: A novel feature fusion with self-adaptive weight method based on deep learning for image classification. In: Hong, R., Cheng, W.-H., Yamasaki, T., Wang, M., Ngo, C.-W. (eds.) PCM 2018. LNCS, vol. 11164, pp. 426–436. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00776-8_39

    Chapter  Google Scholar 

  29. Yang, X., Wan, S., Jin, P.: Domain-invariant region proposal network for cross-domain detection. In: ICME, pp. 1–6 (2020)

    Google Scholar 

  30. Ma, J., Chen, B.: Dual refinement feature pyramid networks for object detection. arXiv preprint arXiv:2012.01733 (2020)

Download references

Acknowledgments

This paper is supported by the National Science Foundation of China (grant no. 62072419).

Author information

Authors and Affiliations

  1. University of Science and Technology of China, Hefei, China

    Jia Xie, Shouhong Wan & Peiquan Jin

  2. Key Laboratory of Electromagnetic Space Information, CAS, Hefei, China

    Jia Xie, Shouhong Wan & Peiquan Jin

Authors
  1. Jia Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shouhong Wan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peiquan Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Peiquan Jin .

Editor information

Editors and Affiliations

  1. University of Vienna, Vienna, Austria

    Christine Strauss

  2. Johannes Kepler University Linz, Linz, Oberösterreich, Austria

    Gabriele Kotsis

  3. Vienna University of Technology, Vienna, Austria

    A Min Tjoa

  4. Johannes Kepler University of Linz, Linz, Austria

    Ismail Khalil

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Xie, J., Wan, S., Jin, P. (2021). DFL-Net: Effective Object Detection via Distinguishable Feature Learning. In: Strauss, C., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2021. Lecture Notes in Computer Science(), vol 12924. Springer, Cham. https://doi.org/10.1007/978-3-030-86475-0_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-86475-0_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-86474-3

  • Online ISBN: 978-3-030-86475-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation