On Accuracy and Speed of Geodesic Regression: Do Geometric Priors Improve Learning on Small Datasets?

CVPRW L3D-IVU

Myers, A., Miolane, N.

A theoretical and empirical study questions whether the accuracy gains of geodesic regression on manifolds justify the significant computational cost compared to linear methods.

Publication Year

Thu, 04/04/2024 - 12:00