Clustering with a Domain-Specific Distance Measure

Abstract

With a point matching distance measure which is invariant under translation, rotation and permutation, we learn 2-D point-set ob(cid:173) jects, by clustering noisy point-set images. Unlike traditional clus(cid:173) tering methods which use distance measures that operate on feature vectors - a representation common to most problem domains - this object-based clustering technique employs a distance measure spe(cid:173) cific to a type of object within a problem domain. Formulating the clustering problem as two nested objective functions, we derive optimization dynamics similar to the Expectation-Maximization algorithm used in mixture models.

Cite

Text

Gold et al. "Clustering with a Domain-Specific Distance Measure." Neural Information Processing Systems, 1993.

Markdown

[Gold et al. "Clustering with a Domain-Specific Distance Measure." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/gold1993neurips-clustering/)

BibTeX

@inproceedings{gold1993neurips-clustering,
  title     = {{Clustering with a Domain-Specific Distance Measure}},
  author    = {Gold, Steven and Mjolsness, Eric and Rangarajan, Anand},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {96-103},
  url       = {https://mlanthology.org/neurips/1993/gold1993neurips-clustering/}
}