ML Anthology

A Semi-Supervised Framework for Mapping Data to the Intrinsic Manifold

Haifeng Gong, Chunhong Pan, Qing Yang, Hanqing Lu, Songde Ma
ICCV 2005 pp. 98-105
doi:10.1109/ICCV.2005.18 /iccv/2005/gong2005iccv-semi/

Abstract

This paper presents a novel scheme for manifold learning. Different from the previous work reducing data to Euclidean space which cannot handle the looped manifold well, we map the scattered data to its intrinsic parameter manifold by semisupervised learning. Given a set of partially labeled points, the map to a specified parameter manifold is computed by an iterative neighborhood average method called anchor points diffusion procedure (APD). We explore this idea on the most frequently used close formed manifolds, Stiefel manifolds whose special cases include hyper sphere and orthogonal group. The experiments show that APD can recover the underlying intrinsic parameters of points on scattered data manifold successfully.

ICCV Semantic Scholar

Cite

Text

Gong et al. "A Semi-Supervised Framework for Mapping Data to the Intrinsic Manifold." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.18

Markdown

[Gong et al. "A Semi-Supervised Framework for Mapping Data to the Intrinsic Manifold." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/gong2005iccv-semi/) doi:10.1109/ICCV.2005.18

BibTeX

@inproceedings{gong2005iccv-semi,
  title     = {{A Semi-Supervised Framework for Mapping Data to the Intrinsic Manifold}},
  author    = {Gong, Haifeng and Pan, Chunhong and Yang, Qing and Lu, Hanqing and Ma, Songde},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {98-105},
  doi       = {10.1109/ICCV.2005.18},
  url       = {https://mlanthology.org/iccv/2005/gong2005iccv-semi/}
}