Advertisement

Statistical and Spatial Consensus Collection for Detector Adaptation

  • Enver Sangineto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8691)

Abstract

The increasing interest in automatic adaptation of pedestrian detectors toward specific scenarios is motivated by the drop of performance of common detectors, especially in video-surveillance low resolution images. Different works have been recently proposed for unsupervised adaptation. However, most of these works do not completely solve the drifting problem: initial false positive target samples used for training can lead the model to drift. We propose to transform the outlier rejection problem in a weak classifier selection approach. A large set of weak classifiers are trained with random subsets of unsupervised target data and their performance is measured on a labeled source dataset. We can then select the most accurate classifiers in order to build an ensemble of weakly dependent detectors for the target domain. The experimental results we obtained on two benchmarks show that our system outperforms other pedestrian adaptation state-of-the-art methods.

Keywords

Pedestrian Detection Unsupervised Domain Adaptation RANSAC 

Supplementary material

978-3-319-10578-9_30_MOESM1_ESM.pdf (298 kb)
Electronic Supplementary Material (PDF 298 KB)

References

  1. 1.
    Aytar, Y., Zisserman, A.: Tabula rasa: Model transfer for object category detection. In: ICCV (2011)Google Scholar
  2. 2.
    Aytar, Y., Zisserman, A.: Enhancing exemplar svms using part level transfer regularization. In: British Machine Vision Conference (2012)Google Scholar
  3. 3.
    Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1-2), 151–175 (2010)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Bourdev, L., Maji, S., Brox, T., Malik, J.: Detecting people using mutually consistent poselet activations. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 168–181. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Cheng, Y.: Mean shift, mode seeking and clustering. IEEE Trans. on PAMI 17(8), 790–799 (1995)CrossRefGoogle Scholar
  6. 6.
    Cortes, C., Mohri, M., Riley, M., Rostamizadeh, A.: Sample selection bias correction theory. In: Proceedings of the 19th International Conference on Algorithmic Learning Theory, pp. 38–53 (2008)Google Scholar
  7. 7.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR. pp. 886–893 (2005)Google Scholar
  8. 8.
    Ding, Y., Jing, X.: Contextual boost for pedestrian detection. In: CVPR. pp. 2895–2902 (2012)Google Scholar
  9. 9.
    Dollár, P., Tu, Z., Perona, P., Belongie, S.: Integral channel features. In: British Machine Vision Conference (2009)Google Scholar
  10. 10.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: An evaluation of the state of the art. IEEE Trans. on Pattern Anal. Mach. Intell. 34(4), 743–761 (2012)CrossRefGoogle Scholar
  11. 11.
    Duda, R.O., Hart, P.E., Strorck, D.G.: Pattern classification (2nd ed.). Wiley Interscience (2000)Google Scholar
  12. 12.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D.A., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. on Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  13. 13.
    Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Golovin, D., Krause, A.: Submodular Function Maximization. In: Tractability: Practical Approaches to Hard Problems (to appear)Google Scholar
  15. 15.
    Golovin, D., Krause, A.: Adaptive submodularity: Theory and applications in active learning and stochastic optimization. Journal of Artificial Intelligence Research (JAIR) 42, 427–486 (2011)zbMATHMathSciNetGoogle Scholar
  16. 16.
    Guillory, A., Bilmes, J.: Simultaneous learning and covering with adversarial noise. In: ICML, pp. 369–376 (2011)Google Scholar
  17. 17.
    Jiang, W., Zavesky, E., Chang, S.F., Loui, A.C.: Cross-domain learning methods for high-level visual concept classification. In: ICIP, pp. 161–164 (2008)Google Scholar
  18. 18.
    Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 158–171. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  19. 19.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by betweenclass attribute transfer. In: CVPR (2009)Google Scholar
  20. 20.
    Lim, J.J., Salakhutdinov, R., Torralba, A.: Transfer learning by borrowing examples for multiclass object detection. In: Neural Information Processing Systems, NIPS (2011)Google Scholar
  21. 21.
    Malisiewicz, T., Gupta, A., Efros, A.A.: Ensemble of exemplar-svms for object detection and beyond. In: ICCV (2011)Google Scholar
  22. 22.
    Matikainen, P., Sukthankar, R., Hebert, M.: Model recommendation for action recognition. In: CVPR, pp. 2256–2263 (2012)Google Scholar
  23. 23.
    Nair, V., Clark, J.J.: An unsupervised, online learning framework for moving object detection. In: CVPR, pp. 317–325 (2004)Google Scholar
  24. 24.
    Ozuysal, M., Calonder, M., Lepetit, V., Fua, P.: Fast keypoint recognition using random ferns. IEEE Trans. Pattern Anal. Mach. Intell. 32(3), 448–461 (2010)CrossRefGoogle Scholar
  25. 25.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transaction on Knowledge and Data Engineering (2010)Google Scholar
  26. 26.
    Roth, P.M., Sternig, S., Grabner, H., Bischof, H.: Classifier grids for robust adaptive object detection. In: CVPR, pp. 2727–2734 (2009)Google Scholar
  27. 27.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  28. 28.
    Sharma, P., Huang, C., Nevatia, R.: Unsupervised incremental learning for improved object detection in a video. In: CVPR, pp. 3298–3305 (2012)Google Scholar
  29. 29.
    Sharma, P., Nevatia, R.: Efficient detector adaptation for object detection in a video. In: CVPR, pp. 3254–3261 (2013)Google Scholar
  30. 30.
    Vázquez, D., López, A.M., Ponsa, D.: Unsupervised domain adaptation of virtual and real worlds for pedestrian detection. In: ICPR, pp. 3492–3495 (2012)Google Scholar
  31. 31.
    Viola, P., Jones, M.: Robust real-time face detection. Int. J. Computer Vision 57(2), 137–154 (2004)CrossRefGoogle Scholar
  32. 32.
    Wang, M., Li, W., Wang, X.: Transferring a generic pedestrian detector towards specific scenes. In: CVPR, pp. 3274–3281 (2012)Google Scholar
  33. 33.
    Wang, M., Wang, X.: Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In: CVPR, pp. 3401–3408 (2011)Google Scholar
  34. 34.
    Wang, X., Hua, G., Han, T.X.: Detection by detections: Non-parametric detector adaptation for a video. In: CVPR, pp. 350–357 (2012)Google Scholar
  35. 35.
    Yang, J., Yan, R., Hauptmann, A.G.: Adapting svm classifiers to data with shifted distributions, pp. 69–76. IEEE Computer Society (2007)Google Scholar
  36. 36.
    Zhang, C., Ma, Y.: Ensemble Machine Learning. Springer (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Enver Sangineto
    • 1
  1. 1.DISIUniversity of TrentoItaly

Personalised recommendations