Advertisement

Unsupervised Detector Adaptation by Joint Dataset Feature Learning

  • Kyaw Kyaw Htike
  • David Hogg
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8671)

Abstract

Object detection is an important step in automated scene understanding. Training state-of-the-art object detectors typically require manual annotation of training data which can be labor-intensive. In this paper, we propose a novel algorithm to automatically adapt a pedestrian detector trained on a generic image dataset to a video in an unsupervised way using joint dataset deep feature learning. Our approach does not require any background subtraction or tracking in the video. Experiments on two challenging video datasets show that our algorithm is effective and outperforms the state-of-the-art approach.

Keywords

Average Precision Deep Learning Neural Information Processing System Linear Support Vector Machine Pedestrian Detector 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (1), pp. 886–893 (2005)Google Scholar
  2. 2.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: CVPR, pp. 304–311 (2009)Google Scholar
  3. 3.
    Everingham, M., Gool, L.J.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (voc) challenge. International Journal of Computer Vision 88(2), 303–338 (2010)CrossRefGoogle Scholar
  4. 4.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)Google Scholar
  5. 5.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp. 2066–2073 (2012)Google Scholar
  6. 6.
    Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: ICCV, pp. 999–1006 (2011)Google Scholar
  7. 7.
    Tang, K., Ramanathan, V., Fei-Fei, L., Koller, D.: Shifting weights: Adapting object detectors from image to video. In: Neural Information Processing Systems (NIPS) (2012)Google Scholar
  8. 8.
    Levina, E., Bickel, P.J.: Maximum likelihood estimation of intrinsic dimension. In: Advances in Neural Information Processing Systems, pp. 777–784 (2004)Google Scholar
  9. 9.
    Martens, J.: Deep learning via hessian-free optimization. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 735–742 (2010)Google Scholar
  10. 10.
    Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Ng, A., Le, Q.V.: On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 265–272 (2011)Google Scholar
  11. 11.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521–1528. IEEE (2011)Google Scholar
  12. 12.
    Wang, M., Li, W., Wang, X.: Transferring a generic pedestrian detector towards specific scenes. In: CVPR, pp. 3274–3281 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Kyaw Kyaw Htike
    • 1
  • David Hogg
    • 1
  1. 1.School of ComputingUniversity of LeedsLeedsUK

Personalised recommendations