Abstract
Transfer learning can counter the heavy-tailed nature of the distribution of training examples over object classes. Here, we study transfer learning for object class detection. Starting from the intuition that “what makes a good detector” should manifest itself in the form of repeatable statistics over existing “good” detectors, we design a low-level feature model that can be used as a prior for learning new object class models from scarce training data. Our priors are structured, capturing dependencies both on the level of individual features and spatially neighboring pairs of features. We confirm experimentally the connection between the information captured by our priors and “good” detectors as well as the connection to transfer learning from sources of different quality. We give an in-depth analysis of our priors on a subset of the challenging PASCAL VOC 2007 data set and demonstrate improved average performance over all 20 classes, achieved without manual intervention.
Chapter PDF
Similar content being viewed by others
Keywords
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
Everingham, M., van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. In: IJCV (2010)
Wang, G., Forsyth, D., Hoiem, D.: Comparative object similarity for improved recognition with few or no examples. In: CVPR (2010)
Salakhutdinov, R., Torralba, A., Tenenbaum, J.: Learning to share visual appearance for multiclass object detection. In: CVPR (2011)
Lim, J.J., Salakhutdinov, R., Torralba, A.: Transfer learning by borrowing examples for multiclass object detection. In: NIPS (2011)
Torralba, A., Murphy, K., Freeman, W.: Sharing visual features for multiclass and multiview object detection. In: CVPR (2004)
Luo, J., Tommasi, T., Caputo, B.: Multiclass transfer learning from unconstrained priors. In: ICCV (2011)
Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)
Farhadi, A., Endres, I., Hoiem, D.: Attribute-centric recognition for cross-category generalization. In: CVPR (2010)
Wang, Y., Mori, G.: A Discriminative Latent Model of Object Classes and Attributes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 155–168. Springer, Heidelberg (2010)
Rohrbach, M., Stark, M., Schiele, B.: Evaluating knowledge transfer and zero-shot learning in a large-scale setting. In: CVPR (2011)
Levi, K., Fink, M., Weiss, Y.: Learning from a small number of training examples by exploiting object categories. In: LCVPR (2004)
Zweig, A., Weinshall, D.: Exploiting object hierarchy: Combining models from different category levels. In: ICCV (2007)
Li, L.J., Wang, C., Lim, Y., Blei, D., Fei-Fei, L.: Building and using a semantivisual image hierarchy. In: CVPR (2010)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI (2010)
Aytar, Y., Zisserman, A.: Tabula rasa: Model transfer for object category detection. In: ICCV (2011)
Stark, M., Goesele, M., Schiele, B.: A shape-based object class model for knowledge transfer. In: ICCV (2009)
Bart, E., Ullman, S.: Cross-generalization: Learning novel classes from a single example by feature replacement. In: CVPR (2005)
Ferrari, V., Zisserman, A.: Learning visual attributes. In: NIPS (2007)
Berg, T.L., Berg, A.C., Shih, J.: Automatic Attribute Discovery and Characterization from Noisy Web Data. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 663–676. Springer, Heidelberg (2010)
Tommasi, T., Orabona, F., Caputo, B.: Safety in numbers: Learning categories from few examples with multi model knowledge transfer. In: CVPR (2010)
Marszalek, M., Schmid, C.: Semantic hierarchies for visual object recognition. In: CVPR (2007)
Bart, E., Ullman, S.: Single-example learning of novel classes using representation by similarity. In: BMVC (2005)
Miller, E., Matsakis, N., Viola, P.: Learning from One Example Through Shared Densities on Transforms. In: CVPR (2000)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. PAMI 28, 594–611 (2006)
Raina, R., Ng, A.Y., Koller, D.: Constructing informative priors using transfer learning. In: ICML (2006)
Elidan, G., Packer, B., Heitz, G., Koller, D.: Convex point estimation using undirected bayesian transfer hierarchies. In: UAI (2008)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)
Fellbaum, C.: WordNet: An Electronical Lexical Database. The MIT Press (1998)
Gabrilovich, E., Markovitch, S.: Computing Semantic Relatedness using Wikipedia-based Explicit Semantic Analysis. In: IJCAI (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gao, T., Stark, M., Koller, D. (2012). What Makes a Good Detector? – Structured Priors for Learning from Few Examples. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7576. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33715-4_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-33715-4_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33714-7
Online ISBN: 978-3-642-33715-4
eBook Packages: Computer ScienceComputer Science (R0)