Skip to main content
SpringerLink
Log in

Edge Detection-Guided Balanced Sampling

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In anchor-based object detection algorithms, achieving a balance between positive and negative samples during training is crucial. Many improved sampling methods have been proposed to address this issue. In our work, we propose an edge-detection guided balanced sampling (EBS) method that introduces edge and contour information from objects to guide the sampling of candidate negative samples and increase the number of hard negative samples to improve sample balance. The EBS method employs a Gaussian filter convolution on the binary image in HSV space to reduce local corner information, and furtherly applies K-means++ clustering to the bounding boxes to reduce redundancy. In the hard negative sample sampling stage of anchor-based detection algorithms, the EBS model selects negative samples with higher IoU values with GT from both the normal candidate negative sample set and the special candidate negative sample set. The latter set contains more hard negative samples, which further improves the sample balance. We conducted comparison experiments using random sampling (RS) and IoU-balanced sampling (IBS) in the RPN network on MSCOCO-2017. Our EBS method achieved a 1.7-point higher higher \(AR_{1000}\) than PRN. In particular, the proposed algorithm performs better on the small-target dataset, which achieves 2.4-point higher \(AR_{S}\) than RPN. The inference fps of RPN and EBS are 22.3 and 22.4, respectively.

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

Similar content being viewed by others

References

  1. Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra r-cnn: towards balanced learning for object detection. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 821–830. https://doi.org/10.1109/CVPR.2019.00091

  2. Wang X, Zhang R, Zhang Z (2022) A novel hybrid sampling method ESMOTE+SSLM for handling the problem of class imbalance with overlap in financial distress detection. Neural Process Lett. https://doi.org/10.1007/s11063-022-10998-0

    Article  Google Scholar 

  3. Zeng F, Chen N, Yang D, Meng Z (2022) Simplified-boosting ensemble convolutional network for text classification. Neural Process Lett. https://doi.org/10.1007/s11063-022-10843-4

    Article  Google Scholar 

  4. Hazarika BB, Gupta D (2022) Density weighted twin support vector machines for binary class imbalance learning. Neural Process Lett 54(2):1091–1130. https://doi.org/10.1007/s11063-021-10671-y

    Article  Google Scholar 

  5. Zhou W, Lian C, Zeng Z, Xu B, Su Y (2021) Improve semi-supervised learning with metric learning clusters and auxiliary fake samples. Neural Process Lett 53:3427–3443. https://doi.org/10.1007/s11063-021-10556-0

    Article  Google Scholar 

  6. Li W, Huang F, Li X, Pan G, Wu F (2019) State distribution-aware sampling for deep q-learning. Neural Process Lett 50:1649–1660. https://doi.org/10.1007/s11063-018-9944-z

    Article  Google Scholar 

  7. Peng C, Liao B (2022) Heavy-head sampling for fast imitation learning of machine learning based combinatorial auction solver. Neural Process Lett. https://doi.org/10.1007/s11063-022-10900-y

    Article  Google Scholar 

  8. Zhu Y, Tan M, Wei J (2022) Robust multi-view classification with sample constraints. Neural Process Lett 54:2589–2612. https://doi.org/10.1007/s11063-021-10483-0

    Article  Google Scholar 

  9. Yang Z, Zhu Y, Liu T, Zhao S, Tao D (2020) Output layer multiplication for class imbalance problem in convolutional neural networks. Neural Process Lett 52:2637–2653. https://doi.org/10.1007/s11063-020-10366-w

    Article  Google Scholar 

  10. Zhao G, Wu Y (2019) Efficient large margin-based feature extraction. Neural Process Lett 50:1257–1279. https://doi.org/10.1007/s11063-018-9920-7

    Article  Google Scholar 

  11. Wang J, Tian L (2019) Stability of inertial neural network with time-varying delays via sampled-data control. Neural Process Lett 50:1123–1138. https://doi.org/10.1007/s11063-018-9905-6

    Article  Google Scholar 

  12. Sanz J, Andina D (2002) Importance sampling and mean-square error in neural detector training. Neural Process Lett 9:259–276. https://doi.org/10.1023/A:1021766820005

    Article  MATH  Google Scholar 

  13. Sanz-González J, Andina D (1999) Performance analysis of neural network detectors by importance sampling techniques. Neural Process Lett 9:257–269. https://doi.org/10.1023/A:1018612207016

    Article  Google Scholar 

  14. Gonzalez AI, Graña M, D’Anjou A, Cottrell F (1997) A sensitivity analysis of the self organizing maps as an adaptive one-pass non-stationary clustering algorithm: the case of color quantization of image sequences. Neural Process Lett 6:77–89. https://doi.org/10.1023/A:1009663723152

    Article  Google Scholar 

  15. Jiang F, Zhu Q, Tian T (2022) Breast cancer detection based on modified Harris Hawks optimization and extreme learning machine embedded with feature weighting. Neural Process Lett. https://doi.org/10.1007/s11063-021-10700-w

    Article  Google Scholar 

  16. Basnet J, Alsadoon A, Prasad P, Aloussi SA, Alsadoon OH (2020) A novel solution of using deep learning for white blood cells classification: enhanced loss function with regularization and weighted loss (ELFRWL). Neural Process Lett 52:1517–1553. https://doi.org/10.1007/s11063-020-10321-9

    Article  Google Scholar 

  17. Liu Z, Pu J, Xu M, Qiu Y (2015) Face recognition via weighted two phase test sample sparse representation. Neural Process Lett 41:43–53. https://doi.org/10.1007/s11063-013-9333-6

    Article  Google Scholar 

  18. Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 761–769. https://doi.org/10.1109/CVPR.2016.89

  19. Wang X, Gupta A (2015) Unsupervised learning of visual representations using videos. In: 2015 IEEE international conference on computer vision (ICCV), pp 2794–2802. https://doi.org/10.1109/ICCV.2015.320

  20. Yin J, Xia P, He J (2019) Online hard region mining for semantic segmentation. Neural Process Lett 50:2665–2679. https://doi.org/10.1007/s11063-019-10047-3

    Article  Google Scholar 

  21. Lin T-Y, Goyal P, Girshick R, He K, Dollár P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318–327. https://doi.org/10.1109/TPAMI.2018.2858826

    Article  Google Scholar 

  22. Cui Y, Jia M, Lin T-Y, Song Y, Belongie S (2019) Class-balanced loss based on effective number of samples. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 9260–9269. https://doi.org/10.1109/CVPR.2019.00949

  23. Li Y, Wang T, Kang B, Tang S, Wang C, Li J, Feng J (2020) Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 10988–10997. https://doi.org/10.1109/CVPR42600.2020.01100

  24. Wang X, Wang H, Zhang C, He Q, Huo L (2022) A sample balance-based regression module for object detection in construction sites. Appl Sci 12(13):6752. https://doi.org/10.3390/app12136752

    Article  Google Scholar 

  25. Huang C, Ding Y, Xu H, Jiao Y, Chen S (2023) An improved class-balanced training sample assignment method for object detection. In: Ninth symposium on novel photoelectronic detection technology and applications, vol. 12617, pp 1044–1049. https://doi.org/10.1117/12.2666120. SPIE

  26. Oksuz K, Cam BC, Kalkan S, Akbas E (2021) Imbalance problems in object detection: a review. IEEE Trans Pattern Anal Mach Intell 43(10):3388–3415. https://doi.org/10.1109/TPAMI.2020.2981890

    Article  Google Scholar 

  27. Malhotra R, Lata K (2023) Analysis of hybridized techniques with class imbalance learning for predicting software maintainability. Int J Reliab Qual Saf Eng 30(02):3388–3415. https://doi.org/10.1142/S0218539323500067

    Article  Google Scholar 

  28. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE conference on computer vision and pattern recognition, pp 580–587. https://doi.org/10.1109/CVPR.2014.81

  29. Girshick R (2015) Fast r-cnn. In: 2015 IEEE international conference on computer vision (ICCV), pp 1440–1448. https://doi.org/10.1109/ICCV.2015.169

  30. Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031

    Article  Google Scholar 

  31. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: Single shot multibox detector. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision - ECCV 2016. Springer, Cham, pp 21–37. https://doi.org/10.1007/978-3-319-46448-0_2

    Chapter  Google Scholar 

  32. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 779–788. https://doi.org/10.1109/CVPR.2016.91

  33. Redmon J, Farhadi A (2017) Yolo9000: Better, faster, stronger. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 6517–6525. https://doi.org/10.1109/CVPR.2017.690

  34. Li D, Yin Z, Wu Z, Liu Q (2021) Classification for tomato disease with imbalanced samples based on td-mobilenetv2. In: 2021 5th international conference on imaging, signal processing and communications (ICISPC), pp 35–39. https://doi.org/10.1109/ICISPC53419.2021.00014

  35. Yu W, Wang J, Cheng G (2021) Object detection in optical remote sensing images based on positive sample reweighting and feature decoupling. In: 2021 IEEE international geoscience and remote sensing symposium IGARSS, pp 4790–4793. https://doi.org/10.1109/IGARSS47720.2021.9554236

  36. Zhen P, Wang S, Zhang S, Yan X, Wang W, Ji Z, Chen H-B (2023) Towards accurate oriented object detection in aerial images with adaptive multi-level feature fusion. ACM Trans Multimedia Comput Commun Appl. https://doi.org/10.1145/3513133

    Article  Google Scholar 

  37. Deng Y, Lan L, You L, Chen K, Peng L, Zhao W, Song B, Wang Y, Ji Z, Zhou X (2023) Automated CT pancreas segmentation for acute pancreatitis patients by combining a novel object detection approach and u-net. Biomed Signal Process Control 81:104430. https://doi.org/10.1016/j.bspc.2022.104430

    Article  Google Scholar 

  38. Suzuki S, Abe K (1985) Topological structural analysis of digitized binary images by border following. Comput Vision Graph Image Process 29(3):396. https://doi.org/10.1016/0734-189X(85)90136-7

    Article  MATH  Google Scholar 

  39. Arthur D, Vassilvitskii S (2007) K-means++: the advantages of careful seeding, vol. 8, pp 1027–1035. https://doi.org/10.1145/1283383.1283494

Download references

Author information

Author notes

  1. Yan Cang and Zihao Wang have contributed equally to this work.

Authors and Affiliations

  1. College of Information and Communication Engineering, Harbin Engineering University, No.145 Nantong street, Nangang District, Harbin, 150001, Heilongjiang, China

    Yan Cang & Zihao Wang

Authors
  1. Yan Cang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zihao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zihao Wang.

Additional information

Publisher's Note

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

Appendix A: More Image Results

Appendix A: More Image Results

Fig. 5
figure 5

More visual examples of the edge boxes generated by the edge-guided module

Full size image
Fig. 6
figure 6

More examples of proposals generated by random sampling (left) and EBS (right) on RPN

Full size image

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

Cang, Y., Wang, Z. Edge Detection-Guided Balanced Sampling. Neural Process Lett 55, 10639–10654 (2023). https://doi.org/10.1007/s11063-023-11342-w

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-023-11342-w

Keywords

Search

Navigation