Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication


Year(s) from:  to 
Author:
Keywords (separated by spaces):

Metric Imitation by Manifold Transfer for Efficient Vision Applications

Dengxin Dai, Till Kroeger, Radu Timofte, Luc Van Gool.
Computer Vision and Pattern Recognition
2015

Abstract

Metric learning has proved very successful. However, humanannotationsarenecessary. Inthispaper,wepropose an unsupervised method, dubbed Metric Imitation (MI), where metrics over cheap features (target features, TFs) are learned by imitating the standard metrics over more sophisticated, off-the-shelf features (source features, SFs) by transferring view-independent property manifold structures. Inparticular,MIconsistsof: 1)quantifyingtheproperties of source metrics as manifold geometry, 2) transferringthemanifoldfromsourcedomaintotargetdomain,and 3)learningamappingofTFssothatthemanifoldisapproximated as well as possible in the mapped feature domain. MI is useful in at least two scenarios where: 1) TFs are moreef?cientcomputationallyandintermsofmemorythan SFs; and 2) SFs contain privileged information, but are not available during testing. For the former, MI is evaluated on image clustering, category-based image retrieval, and instance-based object retrieval, with three SFs and three TFs. Forthelatter,MIistestedonthetaskofexample-based image super-resolution, where high-resolution patches are taken as SFs and low-resolution patches as TFs. Experiments show that MI is able to provide good metrics while avoidingexpensivedatalabelingeffortsandthatitachieves state-of-the-art performance for image super-resolution. In addition, manifold transfer is an interesting direction of transfer learning


Download in pdf format
@InProceedings{eth_biwi_01213,
  author = {Dengxin Dai and Till Kroeger and Radu Timofte and Luc Van Gool.},
  title = {Metric Imitation by Manifold Transfer for Efficient Vision Applications},
  booktitle = {Computer Vision and Pattern Recognition},
  year = {2015},
  keywords = {}
}