Research map / Label-efficient and robust learning / OOD and anomaly detection
EigenScore: OOD Detection using Posterior Covariance in Diffusion Models
Shirin Shoushtari, Yi Wang, Xiao Shi, Salman Asif, Ulugbek S. Kamilov
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 |
|---|---|---|---|
| replace NLL / score-norm metrics with posterior-covariance eigenvalues | diffusion OOD detection · Average over 12 InD-OOD pairs | AUROC: 0.817 (DDPM-OOD) -> 0.869 | Improved |
| use top-K eigenvalues instead of scalar MSE (ablation) | EigenScore · 12 InD-OOD pairs | AUROC: 0.652 -> 0.834 | Improved |
| use EigenScore instead of MSE across pairs (ablation) | EigenScore · SVHN InD pairs vs C10/C100/SVHN | AUROC: MSE 0.994 vs EigenScore 0.990 (SVHN vs C10); C10 vs SVHN 0.184 -> 0.778 | Mixed |
| increase number of timesteps T from 5 to 10 (ablation) | EigenScore · 12 pairs average | AUROC: 0.834 -> 0.808 | Hurt |
| increase repetitions I from 5 to 20 (ablation) | EigenScore · 12 pairs average | AUROC: 0.832 -> 0.834 | No clear effect |
| use K=1 instead of K=3 eigenvalues (ablation) | EigenScore · 12 pairs average | AUROC: 0.834 -> 0.840 | Mixed |
| compare near-OOD C10 vs C100 against DiffPath | EigenScore · C10 vs C100 | AUROC: 0.554 -> 0.884 | Improved |
| compare to DiffPath on TinyImageNet OOD | EigenScore · C10 vs TinyImageNet | AUROC: 0.993 -> 0.973 | Hurt |
Closest papers by meaning
- Backbone-Equated Diffusion OOD via Sparse Internal Snapshots (NeurIPS 2026 · similarity 0.89)
- Improving Out-of-Distribution Detection via Dynamic Covariance Calibration (ICML 2025 · similarity 0.88)
- Out-of-Distribution Detection with a Single Unconditional Diffusion Model (NeurIPS 2024 · similarity 0.88)
- GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection (NeurIPS 2025 · similarity 0.88)
- Detecting Out-of-Distribution Through the Lens of Neural Collapse (CVPR 2025 · similarity 0.87)
- Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity (NeurIPS 2025 · similarity 0.87)
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.
