Weighted Linear Discriminant Analysis based on Class Saliency Information

TL;DR

This paper introduces a weighted LDA variant that incorporates class saliency information to improve classification performance, especially in imbalanced class scenarios, by redefining scatter matrices based on saliency insights.

Contribution

It presents a novel LDA approach leveraging class saliency to enhance robustness against class imbalance and outliers, outperforming traditional methods.

Findings

Improved facial image classification accuracy.

Better handling of imbalanced classes.

Enhanced robustness to outliers.

Abstract

In this paper, we propose a new variant of Linear Discriminant Analysis to overcome underlying drawbacks of traditional LDA and other LDA variants targeting problems involving imbalanced classes. Traditional LDA sets assumptions related to Gaussian class distribution and neglects influence of outlier classes, that might hurt in performance. We exploit intuitions coming from a probabilistic interpretation of visual saliency estimation in order to define saliency of a class in multi-class setting. Such information is then used to redefine the between-class and within-class scatters in a more robust manner. Compared to traditional LDA and other weight-based LDA variants, the proposed method has shown certain improvements on facial image classification problems in publicly available datasets.