Model Transport: Towards Scalable Transfer Learning on Manifolds


Conference Paper


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.

Author(s): Oren Freifeld and Soren Hauberg and Michael J. Black
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Pages: 1378 --1385
Year: 2014
Month: June

Department(s): Perceiving Systems
Research Project(s): Learning on Manifolds
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Columbus, Ohio, USA
Event Name: IEEE Intenational Conference on Computer Vision and Pattern Recognition
Event Place: Columbus, Ohio, USA

Links: pdf


  title = {Model Transport: Towards Scalable Transfer Learning on Manifolds},
  author = {Freifeld, Oren and Hauberg, S{o}ren and Black, Michael J.},
  booktitle = { Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  pages = {1378 --1385},
  address = {Columbus, Ohio, USA},
  month = jun,
  year = {2014},
  month_numeric = {6}