Research map / Label-efficient and robust learning / OOD and anomaly detection
Distribution-Aware Feature Selection for Post-hoc Out-of-Distribution Detection
Max Gutbrod, David Rauber, Christoph Palm
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 |
|---|---|---|---|
| add marginal feature selection (MFS) | kNN · Average over 5 benchmarks | AUROC: 75.83 -> 77.68 | Improved |
| add MFS | MDS · Average over 5 benchmarks | AUROC: 75.77 -> 78.20 | Improved |
| add MFS | MDS++ · Average over 5 benchmarks | AUROC: 79.25 -> 80.41 | Improved |
| add MFS | kNN · MIDOG | AUROC: 70.64 -> 76.66 | Improved |
| add MFS | kNN · PhaKIR | AUROC: 42.41 -> 42.41 | No clear effect |
| add MFS | kNN · Average runtime | runtime reduction: 58.89 % | Improved |
| add whitening before MFS | kNN+MFS · PhaKIR | AUROC: about 14 points | Improved |
| use Wasserstein-1 instead of JS divergence as shift measure (ablation) | kNN+MFS · Medical avg | AUROC: 71.96 -> 72.87 | Improved |
| use mixup proxy-OOD instead of adversarial (ablation) | MDS+MFS · Medical avg | AUROC: 76.42 -> 79.14 | Improved |
| use mixup proxy-OOD instead of adversarial (ablation) | MDS+MFS · Natural avg | AUROC: 77.19 -> 76.79 | Hurt |
| use random feature subsets instead of MFS (ablation) | MDS+MFS · MIDOG and ImageNet-1k | AUROC | Improved |
| use real-OOD validation for selection (ablation) | kNN+MFS · Average over 5 benchmarks | AUROC: +2.41 | Improved |
Closest papers by meaning
- Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection (CVPR 2025 · similarity 0.90)
- Learning to Shape In-distribution Feature Space for Out-of-distribution Detection (NeurIPS 2024 · similarity 0.89)
- Fast Decision Boundary based Out-of-Distribution Detector (ICML 2024 · similarity 0.89)
- CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging (CVPR 2025 · similarity 0.89)
- A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts (NeurIPS 2026 · similarity 0.89)
- Exploiting Discrepancy in Feature Statistic for Out-of-Distribution Detection (AAAI 2024 · similarity 0.89)
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.
