DeepAI AI Chat
Log In Sign Up

A Unified Framework for Domain Adaptation using Metric Learning on Manifolds

by   Sridhar Mahadevan, et al.
University of Massachusetts Amherst
SRI International

We present a novel framework for domain adaptation, whereby both geometric and statistical differences between a labeled source domain and unlabeled target domain can be integrated by exploiting the curved Riemannian geometry of statistical manifolds. Our approach is based on formulating transfer from source to target as a problem of geometric mean metric learning on manifolds. Specifically, we exploit the curved Riemannian manifold geometry of symmetric positive definite (SPD) covariance matrices. We exploit a simple but important observation that as the space of covariance matrices is both a Riemannian space as well as a homogeneous space, the shortest path geodesic between two covariances on the manifold can be computed analytically. Statistics on the SPD matrix manifold, such as the geometric mean of two matrices can be reduced to solving the well-known Riccati equation. We show how the Ricatti-based solution can be constrained to not only reduce the statistical differences between the source and target domains, such as aligning second order covariances and minimizing the maximum mean discrepancy, but also the underlying geometry of the source and target domains using diffusions on the underlying source and target manifolds. A key strength of our proposed approach is that it enables integrating multiple sources of variation between source and target in a unified way, by reducing the combined objective function to a nested set of Ricatti equations where the solution can be represented by a cascaded series of geometric mean computations. In addition to showing the theoretical optimality of our solution, we present detailed experiments using standard transfer learning testbeds from computer vision comparing our proposed algorithms to past work in domain adaptation, showing improved results over a large variety of previous methods.


page 1

page 2

page 3

page 4


Correlation Alignment by Riemannian Metric for Domain Adaptation

Domain adaptation techniques address the problem of reducing the sensiti...

Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation

Domain adaptation (DA) is transfer learning which aims to leverage label...

Geometry-aware Similarity Learning on SPD Manifolds for Visual Recognition

Symmetric Positive Definite (SPD) matrices have been widely used for dat...

Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces

Transfer learning makes use of data or knowledge in one problem to help ...

Museum Exhibit Identification Challenge for Domain Adaptation and Beyond

In this paper, we approach an open problem of artwork identification and...

Kähler information manifolds of signal processing filters in weighted Hardy spaces

We generalize Kähler information manifolds of complex-valued signal proc...