Research map / Label-efficient and robust learning / OOD and anomaly detection
Multidimensional Uncertainty-Aware Evidential Neural Networks
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 |
|---|---|---|---|
| Use WGAN-generated OOD samples and vacuity-based regularization in WENN | WENN · CIFAR10 ID / CIFAR100 OOD | AUROC: 92.5 -> 99.5 | Helped |
| Use vacuity instead of entropy as the WENN OOD score (ablation) | WENN · CIFAR10 ID / CIFAR100 OOD | AUROC: 98.6 -> 99.5 | Helped |
| Use vacuity instead of entropy as the WENN OOD score (ablation) | WENN · SVHN ID / CIFAR10 OOD | AUROC: 99.3 -> 100.0 | Helped |
| Use vacuity instead of entropy as the WENN OOD score (ablation) | WENN · SVHN ID / CIFAR100 OOD | AUROC: 99.3 -> 100.0 | Helped |
| Use vacuity instead of entropy as the WENN OOD score (ablation) | WENN · SVHN ID / LSUN_CR OOD | AUROC: 99.8 -> 99.9 | Helped |
| Use vacuity instead of entropy as the WENN OOD score (ablation) | WENN · CIFAR10 ID / SVHN OOD | AUROC: 100.0 -> 100.0 | No clear effect |
| Use vacuity instead of entropy as the WENN OOD score (ablation) | WENN · FashionMNIST ID / MNIST OOD | AUROC: 100.0 -> 100.0 | No clear effect |
| Use both vacuity and dissonance to distinguish OOD uncertainty from boundary uncertainty | WENN · Synthetic three-class data | uncertainty separation | Helped |
| Use only close adversarial examples as OOD regularizers | ACET · OOD detection | AUROC | Hurt |
| Generate a range of OOD samples during alternating WGAN–ENN training | WENN · OOD detection | AUROC: 92.5 -> 99.5 | Helped |
Closest papers by meaning
- Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty (ICLR 2024 · similarity 0.89)
- Uncertainty Regularized Evidential Regression (AAAI 2024 · similarity 0.88)
- Uncertainty Estimation by Flexible Evidential Deep Learning (NeurIPS 2025 · similarity 0.87)
- Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? (NeurIPS 2024 · similarity 0.87)
- Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models (CVPR 2024 · similarity 0.87)
- Enhancing Uncertainty Estimation and Interpretability with Bayesian Non-negative Decision Layer (ICLR 2025 · 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.