Deep Orientational Representation Learning for Ordinal Regression
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-05 · 48 (5) · 5520-5535
DOI: 10.1109/tpami.2026.3654260 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-05. Verfasst von Gengyun Jia und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Jiangsu Province, Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications.
Abstract (Originalsprache)
Ordinal regression aims to predict ordered classes. Existing methods mainly focus on label distribution shapes and feature distance relationships, while the directional characteristics in the representation space remain underexplored. In this paper, we propose deep orientational representation learning (ORL), aiming to ensure the trajectory of features sequentially connected by ordinal categories approximates a geodesic. We treat the output layer weights as ordinal prototypes and introduce two constraints, the co-directional constraint and the counter-directional constraint. They operate by constraining the angles between pairs of vectors. The former minimizes the angle between vectors with matching start and end categories, while the latter maximizes the angle between vectors whose start categories are the same but whose end categories are on opposite sides. The two constraints optimize the representation from different ordinal directions. ORL is extended to a multi-prototype setting (MORL) to mitigate misalignment between features and oriented prototypes caused by large intra-class variations. Theoretical analysis links ORL to distribution unimodality and distance orderliness, highlighting its advantages. The effectiveness of ORL (MORL) is demonstrated on various tasks including facial age estimation, historical image dating, and aesthetic quality assessment.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Jiangsu Province
- Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications
Zitieren
APA
Jia, G., Ma, X., & Bao, B. K. (2026). Deep Orientational Representation Learning for Ordinal Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(5), 5520-5535. https://doi.org/10.1109/tpami.2026.3654260
Vancouver
Jia G, Ma X, Bao BK. Deep Orientational Representation Learning for Ordinal Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(5):5520-5535. doi:10.1109/tpami.2026.3654260
BibTeX
@article{Jia2026,
author = {Jia, Gengyun and Ma, Xin and Bao, Bing-Kun},
title = {Deep Orientational Representation Learning for Ordinal Regression},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {5},
pages = {5520--5535},
doi = {10.1109/tpami.2026.3654260}
}
EUVIMED