Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

Springer Nature Link
Log in

A multi-phase blending method with incremental intensity for training detection networks

  • Original Article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Object detection is an important topic for visual data processing in the visual computing area. Although a number of approaches have been studied, it still remains a challenge. There is a suitable way to promote image classifiers by blending training with blended images and corresponding blended labels. However, our experiments show that directly moving existing blending methods from classification to object detection will cause the training process become harder and eventually will lead to a bad performance. Inspired by our discovery, this paper presents a multi-phase blending method with incremental blending intensity to improve the accuracy of object detectors and achieve remarkable improvements. Firstly, to adapt blending method to detection task, we propose a smoothly scheduled and incremental blending intensity to control the degree of multi-phase blending. Based on the above dynamic coefficient, we propose an incremental blending method, in which the blending intensity is smoothly increased from zero to full. Therefore, more complex and various data can be created to achieve the goal of regularizing the network. Secondly, we also design an incremental hybrid loss function to replace the original loss function. The blending intensity in our loss function increases smoothly, which is controlled by our scheduled coefficient. Thirdly, we further discard more negative examples in our multi-phase training process than other typical training methods and processes. By doing so, we can regularize the neural network to enhance generalization capability with data diversity and eventually to improve the accuracy in object detection. Another advantage is that there is no negative effect on evaluation because our method is just applied during the training process. Typical experiments show the proposed method improves the generalization of the detection networks. On PASCAL VOC and MS COCO, our method outperforms the state-of-the-art RFBNet of one-stage detectors for real-time processing.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Kán, P., Kafumann, H.: Deeplight: light source estimation for augmented reality using deep learning. Vis. Comput. 35(6–8), 873–883 (2019)

    Article  Google Scholar 

  2. Luciano, L., Hamza, A.B.: Deep similarity network fusion for 3d shape classification. Vis. Comput. 35(6–8), 1171–1180 (2019)

    Article  Google Scholar 

  3. Li, H., He, F., Liang, Y., Quan, Q.: A dividing-based many-objectives evolutionary algorithm for large-scale feature selection. Soft Comput. (2019). https://doi.org/10.1007/s00500-019-04324-5

    Article  Google Scholar 

  4. Zhang, S., He, F., Ren, W., Yao, W.: Joint learning of image detail and transmission map for single image dehazing. Vis. Comput. (2018). https://doi.org/10.1007/s00371-018-1612-9

    Article  Google Scholar 

  5. Pan, Y., He, F., Yu, H.: A correlative denoising autoencoder to model social influence for top-n recommender system. Front. Comput. Sci. (2019). https://doi.org/10.1007/s11704-019-8123-3

    Article  Google Scholar 

  6. Chen, X., He, F., Yu, H.: A matting method based on full feature coverage. Multimed. Tools Appl. 78(9), 11173–11201 (2019)

    Article  Google Scholar 

  7. Yu, H., He, F., Pan, Y.: A novel segmentation model for medical images with intensity inhomogeneity based on adaptive perturbation. Multimed. Tools Appl. 78(9), 11779–11798 (2019)

    Article  Google Scholar 

  8. Li, K., He, F., Yu, H., Chen, X.: A parallel and robust object tracking approach synthesizing adaptive bayesian learning and improved incremental subspace learning. Front. Comput. Sci. 13(5), 1116–1135 (2019)

    Article  Google Scholar 

  9. Yu, H., He, F., Pan, Y.: A novel region-based active contour model via local patch similarity measure for image segmentation. Multimed. Tools Appl. 77(18), 24097–24119 (2018)

    Article  Google Scholar 

  10. Li, K., Fa-Zhi, H.E., Yu, H-p, Chen, X.: A correlative classifiers approach based on particle filter and sample set for tracking occluded target. Appl. Math. J. Chin. Univ. 32(2), 294–312 (2017)

    Article  MathSciNet  Google Scholar 

  11. Li, K., He, F.Z., Yu, H.P.: Robust visual tracking based on convolutional features with illumination and occlusion handing. J. Comput. Sci. Technol. 33(1), 223–236 (2018)

    Article  Google Scholar 

  12. Sun, J., Fa-Zhi, H.E., Chen, Y.L., Xiao, C.: A multiple template approach for robust tracking of fast motion target. Appl. Math. J. Chin. Univ. 31(2), 177–197 (2016)

    Article  MathSciNet  Google Scholar 

  13. Yu, H., He, F., Pan, Y.: A scalable region-based level set method using adaptive bilateral filter for noisy image segmentation. Multimed. Tools Appl. (2019). https://doi.org/10.1007/s11042-019-08493-1

    Article  Google Scholar 

  14. Girshick, R., Donahue, J., Darrell, T., Malik, J.: 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 (2014)

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

    Article  Google Scholar 

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

  17. Zhang, J., Wang, C., Li, C., Qin, H.: Example-based rapid generation of vegetation on terrain via CNN-based distribution learning. Vis. Comput. 35(6–8), 1181–1191 (2019)

    Article  Google Scholar 

  18. Yu, Z., Liu, Q., Liu, G.: Deeper cascaded peak-piloted network for weak expression recognition. Vis. Comput. 34(12), 1691–1699 (2018)

    Article  Google Scholar 

  19. Li, Y., Wang, Z., Yang, X., Wang, M., Poiana, S.I., Chaudhry, E., Zhang, J.: Efficient convolutional hierarchical autoencoder for human motion prediction. Vis. Comput. 35(6–8), 1143–1156 (2019)

    Article  Google Scholar 

  20. Arashloo, S.R., Kittler, J.: Dynamic texture recognition using multiscale binarized statistical image features. IEEE Trans. Multimed. 16(8), 2099–2109 (2014)

    Article  Google Scholar 

  21. Zhang, S., Han, Z., Lai, Y.-K., Zwicker, M., Zhang, H.: Stylistic scene enhancement GAN: mixed stylistic enhancement generation for 3d indoor scenes. Vis. Comput. 35(6–8), 1157–1169 (2019)

    Article  Google Scholar 

  22. Vapnik, V.: Statistical Learning Theory, vol. 3. Wiley, New York (1998)

    MATH  Google Scholar 

  23. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization, arXiv preprint arXiv:1710.09412 (2017)

  24. Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization, arXiv preprint arXiv:1611.03530 (2016)

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

  26. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

  27. Simard, P.Y., LeCun, Y.A., Denker, J.S., Victorri, B.: Transformation invariance in pattern recognition–tangent distance and tangent propagation. In: Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade, pp. 239–274. Springer, Berlin (1998)

    Chapter  Google Scholar 

  28. Chapelle, O., Weston, J., Bottou, L., Vapnik, V.: Vicinal risk minimization. In: Advances in Neural Information Processing Systems, pp. 416–422 (2001)

  29. Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2691–2699 (2015)

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

  31. Guo, H., Mao, Y., Zhang, R.: Mixup as locally linear out-of-manifold regularization, arXiv preprint arXiv:1809.02499 (2018)

  32. Takahashi, R., Matsubara, T., Uehara, K.: Ricap: random image cropping and patching data augmentation for deep CNNs. In: Proceedings of The 10th Asian Conference on Machine Learning, ser. Proceedings of Machine Learning Research, J. Zhu and I. Takeuchi, Eds., vol. 95. PMLR, 14–16 Nov 2018, pp. 786–798

  33. Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104(2), 154–171 (2013)

    Article  Google Scholar 

  34. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

  35. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. (2018)

  36. Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger, arXiv preprint (2017)

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

  38. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: European Conference on Computer Vision, pp. 21–37. Springer (2016)

  39. Liu, S., Huang, D., Wang, A.: Receptive field block net for accurate and fast object detection. In: The European Conference on Computer Vision (ECCV) (2018)

  40. Teng, C.-M.: A comparison of noise handling techniques. In: FLAIRS Conference, pp. 269–273 (2001)

  41. Zhu, X., Wu, X.: Class noise vs. attribute noise: a quantitative study. Artif. Intell. Rev. 22(3), 177–210 (2004)

    Article  Google Scholar 

  42. Bartlett, P.L., Jordan, M.I., McAuliffe, J.D.: Convexity, classification, and risk bounds. J. Am. Stat. Assoc. 101(473), 138–156 (2006)

    Article  MathSciNet  Google Scholar 

  43. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740–755. Springer (2014)

  44. Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts,” arXiv preprint arXiv:1608.03983 (2016)

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

  46. Lin, T.-Y., Dollár, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: CVPR, vol. 1, no. 2, p. 4 (2017)

  47. Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems (NIPS 2016), pp. 379–387. Neural Information Processing Systems Foundation, Inc (2016)

  48. Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks, CoRR, abs/1703.06211, vol. 1, no. 2, p. 3 (2017)

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

  50. Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollár, P.: The IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988. Springer (2017)

  51. Oksuz, K., Can Cam, B., Akbas, E., Kalkan, S.: Localization recall precision (lrp): a new performance metric for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 504–519 (2018)

  52. Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation,” arXiv preprint arXiv:1708.04896 (2017)

  53. Yan, X., He, F., Hou, N., Ai, H.: An efficient particle swarm optimization for large-scale hardware/software co-design system. Int. J. Coop. Inf. Syst. 27(01), 1741001 (2018)

    Article  Google Scholar 

  54. Liu, X., Xu, Q., Wang, N.: A survey on deep neural network-based image captioning. Vis. Comput. 35(3), 445–470 (2019)

    Article  Google Scholar 

  55. Zhang, J., He, F., Chen, Y.: A new haze removal approach for sky/river alike scenes based on external and internal clues. Multimed. Tools Appl. (2019). https://doi.org/10.1007/s11042-019-08399-y

    Article  Google Scholar 

  56. Abbasi, A., Kalkan, S., Sahillioğlu, Y.: Deep 3d semantic scene extrapolation. Vis. Comput. 35(2), 271–279 (2019)

    Article  Google Scholar 

  57. Hou, N., He, F., Zhou, Y., Chen, Y.: An efficient GPU-based parallel tabu search algorithm for hardware/software co-design. Front. Comput. Sci. (2019). https://doi.org/10.1007/s11704-019-8184-3

    Article  Google Scholar 

  58. Li, H., He, F., Yan, X.: IBEA-SVM: an indicator-based evolutionary algorithm based on pre-selection with classification guided by SVM. Appl. Math. J. Chin. Univ. 34, 1–26 (2019)

    Article  MathSciNet  Google Scholar 

  59. Zhang, S., He, F.: DRCDN:learning deep residual convolutional dehazing networks. Vis. Comput. (2019). https://doi.org/10.1007/s00371-019-01774-8

    Article  Google Scholar 

  60. Wu, Y., He, F., Zhang, D., Li, X.: Service-oriented feature-based data exchange for cloud-based design and manufacturing. IEEE Trans. Serv. Comput. 11(2), 341–353 (2018)

    Article  Google Scholar 

  61. Zhang, Z., Han, C., He, S., Liu, X., Zhu, H., Hu, X., Wong, T.-T.: Deep binocular tone mapping. Vis. Comput. 35(6–8), 997–1011 (2019)

    Article  Google Scholar 

  62. Luo, J., He, F., Yong, J.: An efficient and robust bat algorithm with fusion of opposition-based learning and whale optimization algorithm. Intell. Data Anal. 24(3), 500–519 (2020)

    Article  Google Scholar 

  63. Yong, J-s, He, F-z, Li, H-r, Zhou, W-q: A novel bat algorithm based on cross boundary learning and uniform explosion strategy. Appl. Math. J. Chin. Univ. 34(4), 480–502 (2019)

    Article  MathSciNet  Google Scholar 

  64. Zhou, Y., He, F., Qiu, Y.: Dynamic strategy based parallel ant colony optimization on GPUs for TSPs. Sci. China Inf. Sci. 60(6), 068102 (2017)

    Article  Google Scholar 

  65. Rasool, S., Sourin, A.: Real-time haptic interaction with RGBD video streams. Vis. Comput. 32(10), 1311–1321 (2016)

    Article  Google Scholar 

  66. Dal Corso, A., Frisvad, J.R., Mosegaard, J., Baerentzen, J.A.: Interactive directional subsurface scattering and transport of emergent light. Vis. Comput. 33(3), 371–383 (2017)

    Article  Google Scholar 

  67. Eren, M.T., Balcisoy, S.: Evaluation of x-ray visualization techniques for vertical depth judgments in underground exploration. Vis. Comput. 34(3), 405–416 (2018)

    Article  Google Scholar 

Download references

Funding

This study was funded by NSFC (Grant No. 61472289).

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Wuhan University, Wuhan, Hubei, China

    Quan Quan, Fazhi He & Haoran Li

Authors
  1. Quan Quan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fazhi He
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Haoran Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fazhi He.

Ethics declarations

Conflict of interest

All the authors declare that they have no conflict of interest.

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

Quan, Q., He, F. & Li, H. A multi-phase blending method with incremental intensity for training detection networks. Vis Comput 37, 245–259 (2021). https://doi.org/10.1007/s00371-020-01796-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-020-01796-7

Keywords

Search

Navigation