Apprenticeship Learning: Transfer of Knowledge via Dataset Augmentation

  • Miroslav Kobetski
  • Josephine Sullivan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)

Abstract

In visual category recognition there is often a trade-off between fast and powerful classifiers. Complex models often have superior performance to simple ones but are computationally too expensive for many applications. At the same time the performance of simple classifiers is not necessarily limited only by their flexibility but also by the amount of labelled data available for training. We propose a semi-supervised wrapper algorithm named apprenticeship learning, which leverages the strength of slow but powerful classification methods to improve the performance of simpler methods. The powerful classifier parses a large pool of unlabelled data, labelling positive examples to extend the dataset of the simple classifier. We demonstrate apprenticeship learning and its effectiveness by performing experiments on the VOC2007 dataset - one experiment improving detection performance on VOC2007, and one domain adaptation experiment, where the VOC2007 classifier is adapted to a new dataset, collected using a GoPro camera.

Keywords

Object Detection Average Precision Domain Adaptation Multiple Kernel Learn Multiple Instance Learning 
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.

References

  1. 1.
    Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: Proceedings of the International Conference on Computer Vision (2009)Google Scholar
  2. 2.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 1627–1645 (2010)CrossRefGoogle Scholar
  3. 3.
    Felzenszwalb, P., Girshick, R.: D., M.: Cascade object detection with deformable part models. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  4. 4.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings of the Conference on Computational Learning Theory (1998)Google Scholar
  5. 5.
    Feng, H., Chua, T.S.: A bootstrapping approach to annotating large image collection. In: Proceedings of the 5th ACM SIGMM International Workshop on Multimedia Information Retrieval (2003)Google Scholar
  6. 6.
    Levin, A., Viola, P., Freund, Y.: Unsupervised improvement of visual detectors using cotraining. In: Proceedings of the International Conference on Computer Vision (2003)Google Scholar
  7. 7.
    Cowan, I., Tesauro, G., De Sa, V.: Learning classification with unlabeled data. In: Proceedings of the Advances in Neural Information Processing Systems (1993)Google Scholar
  8. 8.
    Saffari, A., Leistner, C., Godec, M.: H., B.: Robust multi-view boosting with priors. In: Proceedings of the European Conference on Computer Vision (2010)Google Scholar
  9. 9.
    Li, L.J., Niebles, J., Fei-Fei, L.: OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning. International Journal of Computer Vision 88, 147–168 (2010)CrossRefGoogle Scholar
  10. 10.
    Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-Supervised Self-Training of Object Detection Models. In: Seventh IEEE Workshop on Applications of Computer Vision (2005)Google Scholar
  11. 11.
    Settles, B.: Active learning. Synthesis Lectures on Artificial Intelligence and Machine Learning (2012)Google Scholar
  12. 12.
    Bucila, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: International Conference on Knowledge Discovery and Data Mining (2006)Google Scholar
  13. 13.
    Bergamo, A., Torresani, L.: Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In: Proceedings of the Advances in Neural Information Processing Systems (2010)Google Scholar
  14. 14.
    Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from Google’s image search. In: Proceedings of the International Conference on Computer Vision (2005)Google Scholar
  15. 15.
    Vijayanarasimhan, S., Keywords, K.G.: to visual categories: Multiple-instance learning for weakly supervised object categorization. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2008)Google Scholar
  16. 16.
    Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence 28, 594–611 (2006)CrossRefGoogle Scholar
  17. 17.
    Schroff, F., Criminisi, A., Zisserman, A.: Harvesting image databases from the web. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 754–766 (2011)CrossRefGoogle Scholar
  18. 18.
    Joachims, T.: Transductive inference for text classification using support vector machines. In: Proceedings of the International Conference on Machine Learning (1999)Google Scholar
  19. 19.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. International Journal of Computer Vision 88, 303–338 (2010)CrossRefGoogle Scholar
  20. 20.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2011)Google Scholar
  21. 21.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Miroslav Kobetski
    • 1
  • Josephine Sullivan
    • 1
  1. 1.Computer Vision and Active PerceptionKTHStockholmSweden

Personalised recommendations