A shape-based object class model for knowledge transfer
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 373-380
- https://doi.org/10.1109/iccv.2009.5459231
Abstract
Object class models trained on hundreds or thousands of images have shown to enable robust detection. Transferring knowledge from such models to new object classes trained from a few or even as little as one training instance however is still in its infancy. This paper designs a shape-based model that allows to easily and explicitly transfer knowledge on three different levels: transfer of individual parts' shape and appearance information, transfer of local symmetry between parts, and transfer of part topology. Due to the factorized form of the model, knowledge can either be transferred for the complete model or just partial knowledge corresponding to certain aspects of the model. The experiments clearly demonstrate that the proposed model is competitive with the state-of-the-art and enables both full and partial knowledge transfer.Keywords
This publication has 25 references indexed in Scilit:
- Decomposition, discovery and detection of visual categories using topic modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Describing Visual Scenes Using Transformed Objects and PartsInternational Journal of Computer Vision, 2007
- From Aardvark to Zorro: A Benchmark for Mammal Image ClassificationInternational Journal of Computer Vision, 2007
- Accurate Object Detection with Deformable Shape Models Learnt from ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- How Good are Local Features for Classes of Geometric ObjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Exploiting Object Hierarchy: Combining Models from Different Category LevelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Image Parsing: Unifying Segmentation, Detection, and RecognitionInternational Journal of Computer Vision, 2005
- Building a classification cascade for visual identification from one examplePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Solvability of linear systems of PDE’s with constant coefficientsProceedings of the American Mathematical Society, 1999