Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
Taeseong Yoon, Heeyoung Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10 | test accuracy: 91.19 -> 92.46 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-100 | test accuracy: 69.40 -> 75.91 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-100 | misclassification detection AUPR: 94.01 -> 96.17 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-100, OOD SVHN | OOD detection AUPR: 75.35 -> 77.90 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10, OOD SVHN | OOD detection AUPR: 91.20 -> 91.58 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10-C severity 5 | distribution shift detection AUPR: 78.52 -> 80.63 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10-C severity 1 | distribution shift detection AUPR: 58.16 -> 58.72 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10-LT (rho=0.01) | test accuracy: 63.73 -> 71.53 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10-LT (rho=0.01) | misclassification detection AUPR: 85.99 -> 91.90 | Improved |
| use MoDEX instead of F-EDL | F-EDL · CIFAR-10-LT (rho=0.01), OOD SVHN | OOD detection AUPR: 62.56 -> 72.05 | Improved |
| use MoDEX instead of F-EDL | F-EDL · DMNIST-LT (rho=0.01) | test accuracy: 67.20 -> 69.42 | Improved |
| use MoDEX instead of F-EDL | F-EDL · DMNIST-LT (rho=0.01), OOD FMNIST | OOD detection AUPR: 96.84 -> 98.88 | Improved |
Closest papers by meaning
- Uncertainty Estimation by Flexible Evidential Deep Learning (NeurIPS 2025 · similarity 0.88)
- Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains (NeurIPS 2026 · similarity 0.85)
- Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space (NeurIPS 2024 · similarity 0.85)
- Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty (ICLR 2024 · similarity 0.85)
- Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models (NeurIPS 2025 · similarity 0.85)
- Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? (NeurIPS 2024 · similarity 0.84)
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.
