Research map / Learning theory and algorithms / Combinatorial and search optimization
A Constrained Deep Neural Network for Ordinal Regression
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with VGG · Historical color images | Accuracy (%): 48.94±2.54 -> 50.12±2.65 | Helped |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with VGG · Historical color images | MAE: 0.81±0.06 -> 0.82±0.05 | Hurt |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with LeNet · MSRA-MM1.0 overall | Accuracy (%): 57.79 -> 59.26 | Helped |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with LeNet · MSRA-MM1.0 overall | MAE: 0.497 -> 0.494 | Helped |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with VGG · Image aesthetics overall | Accuracy (%): 69.45 -> 70.05 | Helped |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with VGG · Image aesthetics overall | MAE: 0.326 -> 0.316 | Helped |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with VGG · Adience Face Dataset | Accuracy (%): 56.7 ± 6.0 -> 57.4 ± 5.8 | Helped |
| Add an adjacent-rank pairwise hinge regularizer to the classification loss | CNNPOR with VGG · Adience Face Dataset | MAE: 0.54 ± 0.08 -> 0.55 ± 0.08 | Hurt |
Closest papers by meaning
- Soft Labels for Ordinal Regression (CVPR 2019 · similarity 0.91)
- Ordinal Regression With Multiple Output CNN for Age Estimation (CVPR 2016 · similarity 0.86)
- Order Regularization on Ordinal Loss for Head Pose, Age and Gaze Estimation (AAAI 2021 · similarity 0.85)
- Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model (NeurIPS 2025 · similarity 0.84)
- SLACE: A Monotone and Balance-Sensitive Loss Function for Ordinal Regression (AAAI 2025 · similarity 0.83)
- Improving Deep Regression with Tightness (ICLR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.