RoDLSR: Robust discriminative least squares regression model for multi-category classification

Lingfeng Wang; Shuaizheng Liu; Chunhong Pan

ICASSP 2017accepted0 citations

RoDLSR: Robust discriminative least squares regression model for multi-category classification

Lingfeng Wang, Shuaizheng Liu, Chunhong Pan

Abstract

Discriminative least squares regression (DLSR) is a simple yet effective method for multi-class classification. One problem of DLSR is that it is lack of robustness to outliers. In order to tackle this difficulty, in this paper, we propose a novel Robust DLSR (RoDLSR) model. The core idea behind RoDLSR is to find and further ignore the outliers among the support vector set. Specifically, we modify the regression targets of outliers by adding an additional item. As a result, the range of regression residuals can be controlled within predefined threshold. Extensive experiments evaluate the effectiveness of RoDLSR, especially on the corrupted databases.

BibTeX

@inproceedings{icassp2017_rodlsrrobustdisc,
  title = {RoDLSR: Robust discriminative least squares regression model for multi-category classification},
  author = {Lingfeng Wang and Shuaizheng Liu and Chunhong Pan},
  booktitle = {ICASSP 2017},
  year = {2017}
}