Model Transport: Towards Scalable Transfer Learning on Manifolds

Oren Freifeld, Søren Hauberg, Michael J. Black

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

295 Downloads (Pure)


We consider the intersection of two research fields: transfer learning and statistics on manifolds. In particular, we consider, for manifold-valued data, transfer learning of tangent-space models such as Gaussians distributions, PCA, regression, or classifiers. Though one would hope to simply use ordinary Rn-transfer learning ideas, the manifold structure prevents it. We overcome this by basing our method on inner-product-preserving parallel transport, a well-known tool widely used in other problems of statistics on manifolds in computer vision. At first, this straightforward idea seems to suffer from an obvious shortcoming: Transporting large datasets is prohibitively expensive, hindering scalability. Fortunately, with our approach, we never transport data. Rather, we show how the statistical models themselves can be transported, and prove that for the tangent-space models above, the transport “commutes” with learning. Consequently, our compact framework, applicable to a large class of manifolds, is not restricted by the size of either the training or test sets. We demonstrate the approach by transferring PCA and logistic-regression models of real-world data involving 3D shapes and image descriptors.
Original languageEnglish
Title of host publicationProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2014
Publication date2014
Publication statusPublished - 2014
Event2014 IEEE Conference on Computer Vision and Pattern Recognition - Columbus, United States
Duration: 23 Jun 201428 Jun 2014


Conference2014 IEEE Conference on Computer Vision and Pattern Recognition
Country/TerritoryUnited States
Internet address
SeriesI E E E Conference on Computer Vision and Pattern Recognition. Proceedings

Bibliographical note

The Open Access version of this CVPR2014 paper is provided by the Computer Vision Foundation. The authoritative version of this paper is posted on IEEE Xplore.


Dive into the research topics of 'Model Transport: Towards Scalable Transfer Learning on Manifolds'. Together they form a unique fingerprint.

Cite this