Model transport: Towards scalable transfer learning on manifolds

Oren Freifeld, Søren Hauberg, Michael J. Black

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

We consider the intersection of two research fields: transfer learning and statistics on manifolds. In particu- lar, we consider, for manifold-valued data, transfer learn- ing of tangent-space models such as Gaussians distribu- tions, 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 statis- tics on manifolds in computer vision. At first, this straight- forward idea seems to suffer from an obvious shortcom- ing: 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, ap- plicable 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 Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages1378-1385
Number of pages8
ISBN (Electronic)9781479951178, 9781479951178
DOIs
StatePublished - 24 Sep 2014
Externally publishedYes
Event27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States
Duration: 23 Jun 201428 Jun 2014

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Country/TerritoryUnited States
CityColumbus
Period23/06/1428/06/14

Keywords

  • Computer Vision
  • Manifold-Valued Data
  • PGA
  • Riemannian Manifolds
  • Scalable
  • Statistics on Manifolds
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Model transport: Towards scalable transfer learning on manifolds'. Together they form a unique fingerprint.

Cite this