Research map / Learning theory and algorithms / Optimal transport
Learning to Count via Unbalanced Optimal Transport
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 |
|---|---|---|---|
| Train by minimizing UOT between predicted density and point annotations rather than using Bayesian loss | VGG-19 crowd counter · NWPU-CROWD | MAE: 105.4 -> 87.8 | Helped |
| Train by minimizing UOT between predicted density and point annotations rather than using Bayesian loss | VGG-19 crowd counter · UCF-QNRF | F-measure: 70.85% -> 74.75% | Helped |
| Use ℓ2 cost rather than ℓ1 cost (ablation) | UOT crowd counter · UCF-QNRF | MAE: 92.7 -> 83.3 | Helped |
| Use ℓ2 cost rather than WFR cost (ablation) | UOT crowd counter · UCF-QNRF | MAE: 85.8 -> 83.3 | Helped |
| Use KL penalty rather than QR penalty with ℓ2 cost (ablation) | UOT crowd counter · UCF-QNRF | MAE: 87.1 -> 83.3 | Helped |
| Use KL penalty rather than QR penalty with ℓ1 cost (ablation) | UOT crowd counter · UCF-QNRF | MAE: 91.6 -> 92.7 | No clear effect |
| Use ℓ2 cost and KL penalty rather than WFR cost and QR penalty (ablation) | UOT crowd counter · UCF-QNRF | MSE: 152.1 -> 142.3 | Helped |
Closest papers by meaning
- Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting (CVPR 2023 · similarity 0.92)
- A Generalized Loss Function for Crowd Counting and Localization (CVPR 2021 · similarity 0.92)
- Counting without Scale: Scale-Consistent Error Correction for Crowd Counting (NeurIPS 2026 · similarity 0.89)
- Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting (CVPR 2025 · similarity 0.87)
- CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models (CVPR 2024 · similarity 0.87)
- Single Domain Generalization for Crowd Counting (CVPR 2024 · similarity 0.86)
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.