de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Multi-view Priors for Learning Detectors from Sparse Viewpoint Data

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons45176

Pepik,  Bojan
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45541

Stark,  Michael
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1312.6095.pdf
(Preprint), 4KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Pepik, B., Stark, M., Gehler, P., & Schiele, B. (2014). Multi-view Priors for Learning Detectors from Sparse Viewpoint Data. In International Conference on Learning Representations 2014 (pp. 1-13). Ithaca, NY: Cornell University. Retrieved from http://arxiv.org/abs/1312.6095.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0019-87A4-4
Abstract
While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer output require larger amounts of training data, preferably well covering the relevant aspects such as viewpoint and fine-grained categories. In this paper, we address this issue from the perspective of transfer learning, and design an object class model that explicitly leverages correlations between visual features. Specifically, our model represents prior distributions over permissible multi-view detectors in a parametric way -- the priors are learned once from training data of a source object class, and can later be used to facilitate the learning of a detector for a target class. As we show in our experiments, this transfer is not only beneficial for detectors based on basic-level category representations, but also enables the robust learning of detectors that represent classes at finer levels of granularity, where training data is typically even scarcer and more unbalanced. As a result, we report largely improved performance in simultaneous 2D object localization and viewpoint estimation on a recent dataset of challenging street scenes.