A novel ordinal regression algorithm, called moving window regression (MWR), is proposed in this paper. First, we propose the notion of relative rank (ρ-rank), which is a new order representation scheme for input and reference instances. Second, we develop global and local relative regressors (ρ-regressors) to predict ρ-ranks within entire and specific rank ranges, respectively. Third, we refine an initial rank estimate iteratively by selecting two reference instances to form a search window and then estimating the ρ-rank within the window. Extensive experiments results show that the proposed algorithm achieves the state-of-the-art performances on various benchmark datasets for facial age estimation and historical color image classification.
Nyeong-Ho Shin, Seon-Ho Lee, and Chang-Su Kim,
"Moving Window Regression: A Novel Approach to Ordinal Regression," accepted to Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.