Self-Supervised Learning Based on Discriminative Nonlinear Features and Its Applications for Pattern Classification

View Sample PDF

Author(s): Qi Tian (University of Texas at San Antonio, USA), Ying Wu (Northwestern University, USA), Jie Yu (University of Texas at San Antonio, USA)and Thomas S. Huang (University of Illinois, USA)
Copyright: 2005
Pages: 25
Source title: Managing Multimedia Semantics
Source Author(s)/Editor(s): Uma Srinivasan (CSIRO ICT Centre, Australia)and Surya Nepal (CSIRO ICT Centre, Australia)
DOI: 10.4018/978-1-59140-569-6.ch003

Keywords: Information Science Reference / Media & Communications / Multimedia Technology

Purchase

View Self-Supervised Learning Based on Discriminative Nonlinear Features and Its Applications for Pattern Classification on the publisher's website for pricing and purchasing information.

Abstract

For learning-based tasks such as image classification and object recognition, the feature dimension is usually very high. The learning is afflicted by the curse of dimensionality as the search space grows exponentially with the dimension. Discriminant expectation maximization (DEM) proposed a framework by applying self-supervised learning in a discriminating subspace. This paper extends the linear DEM to a nonlinear kernel algorithm, Kernel DEM (KDEM), and evaluates KDEM extensively on benchmark image databases and synthetic data. Various comparisons with other state-of-the-art learning techniques are investigated for several tasks of image classification, hand posture recognition and fingertip tracking. Extensive results show the effectiveness of our approach.

The IRMA Community

Research IRM

Self-Supervised Learning Based on Discriminative Nonlinear Features and Its Applications for Pattern Classification

Purchase

Abstract

Related Content

IRMA Sponsors