Research map / Label-efficient and robust learning / Recognition and long-tail
Uncertainty Estimation by Fisher Information-based Evidential Deep Learning
Danruo DENG, Guangyong Chen, Yang YU, Furui Liu, Pheng-Ann Heng
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 Fisher-information-weighted evidential learning | EDL on CIFAR10 classification · CIFAR10 | accuracy: 83.55 ± 0.6 -> 89.20 ± 0.3 | Improved |
| Use Fisher-information-weighted evidential learning | EDL on OOD detection · MNIST → KMNIST | AUPR (Max.P): 97.02 ± 0.8 -> 98.34 ± 0.2 | Improved |
| Use Fisher-information-weighted evidential learning | EDL on few-shot classification · mini-ImageNet 10-way 20-shot | accuracy: 69.29 ± 0.17 -> 78.60 ± 0.08 | Improved |
| Add the negative log-determinant term |I| only (ablation) | EDL · mini-ImageNet 5-way 5-shot | accuracy: 80.38 ± 0.15 -> 81.82 ± 0.14 | Improved |
| Add the negative log-determinant term |I| only (ablation) | EDL · mini-ImageNet 5-way 5-shot | AUPR (OOD, α₀): 76.53 ± 0.27 -> 79.68 ± 0.25 | Improved |
| Add the negative log-determinant term |I| only (ablation) | EDL · mini-ImageNet 5-way 5-shot | AUPR (confidence, Max.α): 93.92 ± 0.09 -> 93.97 ± 0.09 | No clear effect |
| Replace MSE with FIM-weighted MSE only (ablation) | EDL · mini-ImageNet 5-way 5-shot | accuracy: 80.38 ± 0.15 -> 81.27 ± 0.14 | Improved |
| Replace MSE with FIM-weighted MSE only (ablation) | EDL · mini-ImageNet 5-way 5-shot | AUPR (confidence, Max.α): 93.92 ± 0.09 -> 94.42 ± 0.08 | Improved |
| Replace MSE with FIM-weighted MSE only (ablation) | EDL · mini-ImageNet 5-way 5-shot | AUPR (OOD, α₀): 76.53 ± 0.27 -> 81.75 ± 0.22 | Improved |
| Use both FIM-weighted MSE and the |I| term (ablation) | EDL · mini-ImageNet 5-way 5-shot | accuracy: 80.38 ± 0.15 -> 82.00 ± 0.14 | Improved |
| Use both FIM-weighted MSE and the |I| term (ablation) | EDL · mini-ImageNet 5-way 5-shot | AUPR (confidence, Max.α): 93.92 ± 0.09 -> 94.09 ± 0.09 | Improved |
| Use both FIM-weighted MSE and the |I| term (ablation) | EDL · mini-ImageNet 5-way 5-shot | AUPR (OOD, α₀): 76.53 ± 0.27 -> 82.48 ± 0.20 | Improved |
Closest papers by meaning
- Uncertainty Estimation by Flexible Evidential Deep Learning (NeurIPS 2025 · similarity 0.91)
- Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? (NeurIPS 2024 · similarity 0.90)
- Uncertainty Estimation by Density Aware Evidential Deep Learning (ICML 2024 · similarity 0.89)
- Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods? (ICML 2024 · similarity 0.88)
- Calibrating LLMs with Information-Theoretic Evidential Deep Learning (ICLR 2025 · similarity 0.87)
- Uncertainty Regularized Evidential Regression (AAAI 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.
