Advertisement

Deep Regression Tracking with Shrinkage Loss

  • Xiankai Lu
  • Chao MaEmail author
  • Bingbing Ni
  • Xiaokang Yang
  • Ian Reid
  • Ming-Hsuan Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11218)

Abstract

Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions. Due to the potential for fast-tracking and easy implementation, regression trackers have recently received increasing attention. However, state-of-the-art deep regression trackers do not perform as well as discriminative correlation filters (DCFs) trackers. We identify the main bottleneck of training regression networks as extreme foreground-background data imbalance. To balance training data, we propose a novel shrinkage loss to penalize the importance of easy training data. Additionally, we apply residual connections to fuse multiple convolutional layers as well as their output response maps. Without bells and whistles, the proposed deep regression tracking method performs favorably against state-of-the-art trackers, especially in comparison with DCFs trackers, on five benchmark datasets including OTB-2013, OTB-2015, Temple-128, UAV-123 and VOT-2016.

Keywords

Regression networks Shrinkage loss Object tracking 

Notes

Acknowledgments

This work is supported in part by the National Key Research and Development Program of China (2016YFB1001003), NSFC (61527804, 61521062, U1611461, 61502301, and 61671298), the 111 Program (B07022), and STCSM (17511105401 and 18DZ2270700). C. Ma and I. Reid acknowledge the support of the Australian Research Council through the Centre of Excellence for Robotic Vision (CE140100016) and Laureate Fellowship (FL130100102). B. Ni is supported by China’s Thousand Youth Talents Plan. M.-H. Yang is supported by NSF CAREER (1149783).

Supplementary material

474202_1_En_22_MOESM1_ESM.pdf (724 kb)
Supplementary material 1 (pdf 723 KB)

References

  1. 1.
    Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Convolutional features for correlation filter based visual tracking. In: ICCV Workshops (2015)Google Scholar
  2. 2.
    Qi, Y., et al.: Hedged deep tracking. In: CVPR (2016)Google Scholar
  3. 3.
    Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Hierarchical convolutional features for visual tracking. In: ICCV (2015)Google Scholar
  4. 4.
    Danelljan, M., Robinson, A., Shahbaz Khan, F., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 472–488. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_29CrossRefGoogle Scholar
  5. 5.
    Danelljan, M., Bhat, G., Shahbaz Khan, F., Felsberg, M.: Eco: efficient convolution operators for tracking. In: CVPR (2017)Google Scholar
  6. 6.
    Wang, L., Ouyang, W., Wang, X., Lu, H.: Visual tracking with fully convolutional networks. In: ICCV (2015)Google Scholar
  7. 7.
    Wang, L., Ouyang, W., Wang, X., Lu, H.: STCT: sequentially training convolutional networks for visual tracking. In: CVPR (2016)Google Scholar
  8. 8.
    Song, Y., Ma, C., Gong, L., Zhang, J., Lau, R.W.H., Yang, M.H.: Crest: convolutional residual learning for visual tracking. In: ICCV (2017)Google Scholar
  9. 9.
    Wu, Y., Lim, J., Yang, M.: Object tracking benchmark. TPAMI 37(9), 585–595 (2015)Google Scholar
  10. 10.
    Kristan, M., et al.: The visual object tracking VOT2016 challenge results. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 777–823. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_54Google Scholar
  11. 11.
    He, H., Garcia, E.A.: Learning from imbalanced data. TKDE 21(9), 1263–1284 (2009)Google Scholar
  12. 12.
    Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Learning spatially regularized correlation filters for visual tracking. In: ICCV (2015)Google Scholar
  13. 13.
    Lukezic, A., Vojir, T., Zajc, L.C., Matas, J., Kristan, M.: Discriminative correlation filter with channel and spatial reliability. In: CVPR (2017)Google Scholar
  14. 14.
    Kiani Galoogahi, H., Fagg, A., Lucey, S.: Learning background-aware correlation filters for visual tracking. In: ICCV (2017)Google Scholar
  15. 15.
    Copas, J.B.: Regression, prediction and shrinkage. J. Roy. Stat. Soc. 45, 311–354 (1983)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollr, P.: Focal loss for dense object detection. In: ICCV (2017)Google Scholar
  17. 17.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)Google Scholar
  18. 18.
    Salti, S., Cavallaro, A., di Stefano, L.: Adaptive appearance modeling for video tracking: survey and evaluation. TIP 21(10), 4334–4348 (2012)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Smeulders, A.W.M., Chu, D.M., Cucchiara, R., Calderara, S., Dehghan, A., Shah, M.: Visual tracking: an experimental survey. TPAMI 36(7), 1442–1468 (2014)Google Scholar
  20. 20.
    Wang, N., Shi, J., Yeung, D.Y., Jia, J.: Understanding and diagnosing visual tracking systems. In: ICCV (2015)Google Scholar
  21. 21.
    Hua, Y., Alahari, K., Schmid, C.: Online object tracking with proposal selection. In: ICCV (2015)Google Scholar
  22. 22.
    Zhu, G., Porikli, F., Li, H.: Beyond local search: tracking objects everywhere with instance-specific proposals. In: CVPR (2016)Google Scholar
  23. 23.
    Babenko, B., Yang, M., Belongie, S.J.: Robust object tracking with online multiple instance learning. TPAMI 33(8), 1619–1632 (2011)CrossRefGoogle Scholar
  24. 24.
    Hare, S., Saffari, A., Torr, P.H.: Struck: structured output tracking with kernels. In: ICCV (2011)Google Scholar
  25. 25.
    Ning, J., Yang, J., Jiang, S., Zhang, L., Yang, M.: Object tracking via dual linear structured SVM and explicit feature map. In: CVPR (2016)Google Scholar
  26. 26.
    Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR (2016)Google Scholar
  27. 27.
    Li, H., Li, Y., Porikli, F.: Deeptrack: learning discriminative feature representations by convolutional neural networks for visual tracking. In: BMVC (2014)Google Scholar
  28. 28.
    Hong, S., You, T., Kwak, S., Han, B.: Online tracking by learning discriminative saliency map with convolutional neural network. In: ICML (2015)Google Scholar
  29. 29.
    Girshick, R.B.: Fast R-CNN. In: ICCV (2015)Google Scholar
  30. 30.
    Bolme, D.S., Beveridge, J.R., Draper, B.A., Lui, Y.M.: Visual object tracking using adaptive correlation filters. In: CVPR (2010)Google Scholar
  31. 31.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. TPAMI 37(3), 583–596 (2015)CrossRefGoogle Scholar
  32. 32.
    Ma, C., Yang, X., Zhang, C., Yang, M.H.: Long-term correlation tracking. In: CVPR (2015)Google Scholar
  33. 33.
    Ma, C., Huang, J.B., Yang, X., Yang, M.H.: Adaptive correlation filters with long-term and short-term memory for object tracking. IJCV 10, 1–26 (2018)Google Scholar
  34. 34.
    Wang, M., Liu, Y., Huang, Z.: Large margin object tracking with circulant feature maps. In: CVPR (2017)Google Scholar
  35. 35.
    Zhang, T., Xu, C., Yang, M.H.: Multi-task correlation particle filter for robust object tracking. In: CVPR (2017)Google Scholar
  36. 36.
    Zadrozny, B., Langford, J., Abe, N.: Cost-sensitive learning by cost-proportionate example weighting. In: ICDM (2003)Google Scholar
  37. 37.
    Kukar, M., Kononenko, I.: Cost-sensitive learning with neural networks. In: ECAI (1998)Google Scholar
  38. 38.
    Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: CVPR (2016)Google Scholar
  39. 39.
    Dong, Q., Gong, S., Zhu, X.: Class rectification hard mining for imbalanced deep learning. In: ICCV (2017)Google Scholar
  40. 40.
    Maciejewski, T., Stefanowski, J.: Local neighbourhood extension of SMOTE for mining imbalanced data. In: CIDM (2011)Google Scholar
  41. 41.
    Khan, S.H., Hayat, M., Bennamoun, M., Sohel, F.A., Togneri, R.: Cost-sensitive learning of deep feature representations from imbalanced data. TNNLS 99, 1–17 (2017)Google Scholar
  42. 42.
    Tang, Y., Zhang, Y., Chawla, N.V., Krasser, S.: SVMS modeling for highly imbalanced classification. IEEE Trans. Cybern 39(1), 281–288 (2009)Google Scholar
  43. 43.
    Ting, K.M.: A comparative study of cost-sensitive boosting algorithms. In: ICML (2000)Google Scholar
  44. 44.
    Li, H., Li, Y., Porikli, F.M.: Robust online visual tracking with a single convolutional neural network. In: ACCV (2014)Google Scholar
  45. 45.
    Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.S.: Fully-convolutional siamese networks for object tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 850–865. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_56CrossRefGoogle Scholar
  46. 46.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  47. 47.
    Danelljan, M., Khan, F.S., Felsberg, M., van de Weijer, J.: Adaptive color attributes for real-time visual tracking. In: CVPR (2014)Google Scholar
  48. 48.
    Danelljan, M., Häger, G., Khan, F.S., Felsberg, M.: Accurate scale estimation for robust visual tracking. In: BMVC (2014)Google Scholar
  49. 49.
    Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: CVPR (2013)Google Scholar
  50. 50.
    Liang, P., Blasch, E., Ling, H.: Encoding color information for visual tracking: algorithms and benchmark. TIP 24(12), 5630–5644 (2015)MathSciNetCrossRefGoogle Scholar
  51. 51.
    Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445–461. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_27CrossRefGoogle Scholar
  52. 52.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACMMM (2014)Google Scholar
  53. 53.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR (2014)Google Scholar
  54. 54.
    Held, D., Thrun, S., Savarese, S.: Learning to track at 100 FPS with deep regression networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 749–765. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_45CrossRefGoogle Scholar
  55. 55.
    Hong, Z., Chen, Z., Wang, C., Mei, X., Prokhorov, D.V., Tao, D.: Multi-store tracker (muster): a cognitive psychology inspired approach to object tracking. In: CVPR (2015)Google Scholar
  56. 56.
    Zhang, J., Ma, S., Sclaroff, S.: MEEM: robust tracking via multiple experts using entropy minimization. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 188–203. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10599-4_13CrossRefGoogle Scholar
  57. 57.
    Gao, J., Ling, H., Hu, W., Xing, J.: Transfer learning based visual tracking with gaussian processes regression. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 188–203. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10578-9_13CrossRefGoogle Scholar
  58. 58.
    Tao, R., Gavves, E., Smeulders, A.W.M.: Siamese instance search for tracking. In: CVPR (2016)Google Scholar
  59. 59.
    Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: CVPR (2006)Google Scholar
  60. 60.
    Li, Y., Zhu, J.: A scale adaptive kernel correlation filter tracker with feature integration. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8926, pp. 254–265. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-16181-5_18CrossRefGoogle Scholar
  61. 61.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33765-9_50CrossRefGoogle Scholar
  62. 62.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  63. 63.
    Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.H.S.: Staple: complementary learners for real-time tracking. In: CVPR (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Xiankai Lu
    • 1
    • 3
  • Chao Ma
    • 2
    Email author
  • Bingbing Ni
    • 1
    • 4
  • Xiaokang Yang
    • 1
    • 4
  • Ian Reid
    • 2
  • Ming-Hsuan Yang
    • 5
    • 6
  1. 1.Shanghai Jiao Tong UniversityShanghaiChina
  2. 2.The University of AdelaideAdelaideAustralia
  3. 3.Inception Institute of Artificial IntelligenceAbu DhabiUAE
  4. 4.SJTU-UCLA Joint Center for Machine Perception and InferenceShanghaiChina
  5. 5.University of California at MercedMercedUSA
  6. 6.Google Inc.Menlo ParkUSA

Personalised recommendations