Deep Extrinsic Manifold Representation for Vision Tasks

arXiv:2404.00544v1 Announce Type: new
Abstract: Non-Euclidean data is frequently encountered across different fields, yet there is limited literature that addresses the fundamental challenge of training neural networks with manifold representations as outputs. We introduce the trick named Deep Extrinsic Manifold Representation (DEMR) for visual tasks in this context. DEMR incorporates extrinsic manifold embedding into deep neural networks, which helps generate manifold representations. The DEMR approach does not directly optimize the complex geodesic loss. Instead, it focuses on optimizing the computation …

abstract arxiv challenge context cs.ai cs.cv data embedding fields literature manifold networks neural networks non-euclidean representation tasks training trick type vision visual