VEHICLE TYPE DETECTION BASED ON RETINANET WITH ADAPTIVE LEARNING RATE ATTENUATION

Yiliu Xu, Peng He, Hui Wang, Ting Dong, and Pan Shao

References

  1. [1] C. Chen and F. Qi, Review on development of convolutionalneural network and its application in computer vision, Com-puter Science, 46(03), 2019, 63–73.
  2. [2] Y. Ida, Y. Fujiwara, and S. Iwamura, Adaptive learningrate via covariance matrix based preconditioning for deepneural networks, International Joint Conference on ArtificialIntelligence, Melbourne, VIC, Australia, 2017, 1923–1929.
  3. [3] H. Zhao, F. Liu, H. Zhang, and Z. Liang, Research on a learningrate with energy index in deep learning, Neural Networks, 110,2019, 225–231.
  4. [4] B. Chandra and R.K. Sharma, Deep learning with adap-tive learning rate using Laplacian score, Expert Systems withApplications, 63, 2016, 1–7.
  5. [5] L. Fan, T. Zhang, X. Zhao, H. Wang, and M. Zheng, Deeptopology network: A framework based on feedback adjustmentlearning rate for image classification, Advanced Engineering In-formatics, 42, 2019. https://doi.org/10.1016/j.aei.2019.100935.
  6. [6] J. Redmon, S.K. Divvala, R.B. Girshick, and A. Farhadi,You only look once: Unified, real-time object detection,International Conference on Computer Vision and PatternRecogintion, Las Vegas, NV, United states, 2016, 779–788.
  7. [7] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S.E. Reed,C.-Y. Fu, et al., SSD: Single Shot MultiBox Detector, EuropeanConference on Computer Vision, Amsterdam, Netherlands,2016, 21–37.
  8. [8] R.B. Girshick, J. Donahue, T. Darrell, and J. Malik, Richfeature hierarchies for accurate object detection and semanticsegmentation, International Conference on Computer Visionand Pattern Recogintion, Columbus, OH, United states, 2014,580–587.7
  9. [9] T.-Y. Lin, P. Goyal, R.B. Girshick, K. He, and P. Doll´ar, Focalloss for dense object detection, International Conference onComputer Vision, Venice, Italy, 2017, 2999–3007.
  10. [10] M. Altun and O. Pekcan, A modified approach to cross entropymethod: Elitist stepped distribution algorithm, Applied SoftComputing, 58, 2017, 756–769.
  11. [11] D. Ren, C. Zhang, S. Ren, Z. Zhang, J.H. Wang, and A.X. Lu,An improved approach of cars for Longjing tea detection basedon near infrared spectra, International Journal of Robotics &Automation, 33(1), 2018, 97–103.
  12. [12] P. Shao, W. Shi, and M. Hao, Indicator-Kriging-integratedevidence theory for unsupervised change detection in remotelysensed imagery, IEEE Journal of Selected Topics in Ap-plied Earth Observations and Remote Sensing, 11(12), 2018,4649–4663.
  13. [13] A. Arinaldi, J.A. Pradana, and A.A. Gurusinga, Detection andclassification of vehicles for traffic video analytics, ProcediaComputer Science, 144, 2018, 259–268.
  14. [14] T. Takase, S. Oyama, and M. Kurihara, Effective neuralnetwork training with adaptive learning rate based on trainingloss, Neural Networks, 101, 2018, 68–78.
  15. [15] Y. Xu, H. Wang, X. Liu, and W. Sun’s, An improved multi-branch residual network based on random multiplier and adap-tive cosine learning rate method, Journal of Visual Commu-nication and Image Representation, 59, 2019, 363–370.
  16. [16] K. Yamada, H. Mori, T. Youkawa, Y. Miyauchi, S. Izumi,M. Yoshimoto, et al., Adaptive learning rate adjustment withshort-term pre-training in data-parallel deep learning, 2018IEEE International Workshop on Signal Processing Systems(SiPS ), Cape Town, South Africa, 2018, 100–105.
  17. [17] L. Blier, P. Wolinski, and Y. Ollivier, Learning with randomlearning rates, European Conference on Machine Learning andPrinciples and Practice of Knowledge Discovery in Databases,Wurzburg, Germany, 2019, 449–464.
  18. [18] S. Ren, K. He, R.B. Girshick, and J. Sun, Faster R-CNN:Towards real-time object detection with region proposal net-works, IEEE Transactions on Pattern Analysis and Machine.Intelligence, 39(6), 2017, 1137–1149.
  19. [19] A. Krizhevsky, I. Sutskever, and G.E. Hinton, ImageNet clas-sification with deep convolutional neural networks, Communi-cations of the ACM, 60(6), 2017, 84–90.
  20. [20] Y. Liu, B.C. Yin, J. Yu, and Z.F. Wang, Image classificationbased on convolutional neural networks with cross-level strat-egy, Multimedia Tools and Applications, 2017, 11065–11079.
  21. [21] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S.E. Reed, D.Anguelov, et al., Going deeper with convolutions, InternationalConference on Computer Vision and Pattern, Boston, MA,2015, 1–9.
  22. [22] T.-Y. Lin, P. Doll´ar, R.B. Girshick, K. He, B. Hariharan, andS.J. Belongie, Feature pyramid networks for object detection,International Conference on Computer Vision and Pattern,Honolulu, HI, United states, 2017, 936–944.
  23. [23] K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learningfor image recognition, International Conference on ComputerVision and Pattern, Las Vegas, NV, United states, 2016,770–778.

Important Links:

Go Back