CORE: Learning consistent ordinal representations with convex optimization for ordinal estimation

doi:10.1016/j.patcog.2024.110748

CORE: Learning consistent ordinal representations with convex optimization for ordinal estimation

2024-12-01

0

PRE

AI

DOI：10.1016/j.patcog.2024.110748

Original

Original request for help

Save

Abstract

En 中文

Image ordinal estimation is to estimate the ordinal label of a given image. Existing methods primarily rely on ordinal regression, mapping feature representations directly to ordinal labels. However, these methods often struggle to preserve the inherent order within the learned feature representations. To this end, this paper proposes learning intrinsic Consistent Ordinal REpresentations (CORE), a novel approach that learns intrinsic ordinal relationships directly from ground-truth labels. First, it constructs an ordinal manifold using an ordinal totally ordered set ( toset ) distribution (OTD), capturing the inherent order of labels while regularizing feature embeddings. Second, the CORE leverages the toset distribution to convert both feature representations and labels into a unified embedding space, enabling consistent manifold alignment. Third, CORE employs an ordinal prototype-constrained convex programming formulation with dual decomposition, minimizing the Kullback-Leibler (KL) divergence between the toset distributions of labels and feature representations. Extensive experiments demonstrate that CORE, when combined with existing deep ordinal regression methods, significantly improves their performance in preserving ordinal relationships and achieves superior quantitative results across four real-world scenarios.

Keywords:

Ordinal regression

Image ordinal estimation

Convex optimization

Dual decomposition

CORE: Learning consistent ordinal representations with convex optimization for ordinal estimation

Abstract

Journal

Organization