Learning Effective Image Metrics from Few Pairwise Examples

Authors:
Hwann-Tzong Chen;Tyng-Luh Liu;Chiou-Shann Fuh
Affiliations:
Academia Sinica and National Taiwan University;Academia Sinica;National Taiwan University
Venue:
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Year:
2005

Citing 0
Cited 4

A novel multi-view learning developed from single-view patterns

Pattern Recognition
Letters: Orthogonal tensor rank one differential graph preserving projections with its application to facial expression recognition

Neurocomputing
Block principal component analysis with L1-norm for image analysis

Pattern Recognition Letters
A novel face recognition method based on sub-pattern and tensor

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new approach to learning image metrics. The main advantage of our method lies in a formulation that requires only a few pairwise examples. Apparently, based on the little amount of side-information, it would take a very effective learning scheme to yield a useful image metric. Our algorithm achieves this goal by addressing two key issues. First, we establish a global-local (glocal) image representation that induces two structure-meaningful vector spaces to respectively describe the global and the local image properties. Second, we develop a metric optimization framework that finds an optimal bilinear transform to best explain the given side-information. We emphasize it is the glocal image representation that makes the use of bilinear transform more powerful. Experimental results on classifications of face images and visual tracking are included to demonstrate the contributions of the proposed method.