Wasserstein K-Means for Clustering Tomographic Projections.

Rohan Rao, Amit Moscovich, Amit Singer

Research output: Contribution to conferencePaperpeer-review

Abstract

Motivated by the 2D class averaging problem in single-particle cryo-electron microscopy (cryo-EM), we present a k-means algorithm based on a rotationally-invariant Wasserstein metric for images. Unlike existing methods that are based on Euclidean (L2) distances, we prove that the Wasserstein metric better accommodates for the out-of-plane angular differences between different particle views. We demonstrate on a synthetic dataset that our method gives superior results compared to an L2 baseline. Furthermore, there is little computational overhead, thanks to the use of a fast linear-time approximation to the Wasserstein-1 metric, also known as the Earthmover's distance.
Original languageEnglish
StatePublished - 2020
Externally publishedYes
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: 6 Dec 202012 Dec 2020

Conference

Conference34th Conference on Neural Information Processing Systems, NeurIPS 2020
CityVirtual, Online
Period6/12/2012/12/20

Fingerprint

Dive into the research topics of 'Wasserstein K-Means for Clustering Tomographic Projections.'. Together they form a unique fingerprint.

Cite this