Diffuse Interface Methods for Multiclass Segmentation of High-Dimensional Data

Abstract

We present two graph-based algorithms for multiclass segmentation of high-dimensional data, motivated by the binary diffuse interface model. One algorithm generalizes Ginzburg? Landau \201GL\202 functional minimization on graphs to the Gibbs simplex. The other algorithm uses a reduction of GL minimization, based on the Merriman-Bence-Osher scheme for motion by mean curvature. These yield accurate and efficient algorithms for semi-supervised learning. Our algorithms outperform existing methods, including supervised learning approaches on the benchmark datasets that we used. We refer to Garcia-Cardona (2014) for a more detailed illustration of the methods, as well as different experimental examples.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 04, 2014
Accession Number
ADA600498

Entities

People

  • Allon G. Percus
  • Andrea Bertozzi
  • Arjuna Flenner
  • Cristina Garcia-Cardona
  • Ekaterina Merkurjev

Organizations

  • University of California, Los Angeles

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Space

DTIC Thesaurus Topics

  • Algorithms
  • Applied Mathematics
  • Computer Science
  • Computer Vision
  • Curvature
  • Differential Equations
  • Eigenvectors
  • Electronic Mail
  • Equations
  • Image Processing
  • Learning
  • Linear Algebra
  • Machine Learning
  • Mathematics
  • Semi-Supervised Learning
  • Supervised Machine Learning
  • United States

Fields of Study

  • Computer science

Readers

  • Graph Algorithms and Convex Optimization.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms