Research map / Label-efficient and robust learning / OOD and anomaly detection
SCOD: From Heuristics to Theory
Vojtech Franc, Jakub Paplham, Daniel Prusa
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 the SIRC combination with the theoretically optimal linear combination of conditional risk and OOD/ID likelihood ratio (ablation) | SCOD selector (plugin, clean-OOD LR) · ImageNet vs SSB_Hard | AuSRT: 13.24 -> 6.10 | Improved |
| combine MSP with the learned likelihood ratio through the linear score instead of using MSP alone | SCOD selector · ImageNet vs SSB_Hard | AuSRT: 17.47 -> 6.10 | Improved |
| use the corrected sigmoid instead of the standard sigmoid to learn the likelihood ratio (ablation) | Linear double-score selector (POSCOD) · ImageNet vs SSB_Hard | AuSRT: 7.28 -> 6.37 | Improved |
| use the corrected sigmoid instead of the standard sigmoid for SIRC (ablation) | SIRC selector · ImageNet vs iNaturalist | AuSRT: 4.34 -> 8.02 | Hurt |
| replace SIRC with the linear strategy using POSCOD likelihood ratio | SCOD selector · ImageNet, five OOD sets | AuSRT: 14.27 -> 6.37 (SSB_Hard) | Improved |
| use linear combination with contemporary OOD scores instead of SIRC | SCOD selector · ImageNet, contemporary OOD scores | AuSRT | Mixed |
| vary relative cost alpha from 0.1 to 0.9 for Linear vs SIRC (ablation) | POSCOD linear strategy · ImageNet, five OOD sets | AuSRT: SSB_Hard alpha=0.9: 20.13 -> 9.97 | Improved |
| reduce OOD proportion in the training mixture from 0.5 to 0.1 (ablation) | POSCOD · ImageNet vs SSB_Hard | AuSRT: 5.88 -> 17.20 | Hurt |
| tune strategy hyperparameters on test data (tuned vs plugin) (ablation) | Linear and SIRC selectors · ImageNet vs SSB_Hard | AuSRT: Linear 6.10 -> 5.88; SIRC 13.24 -> 6.59 | Improved |
Closest papers by meaning
- Plugin estimators for selective classification with out-of-distribution detection (ICLR 2024 · similarity 0.91)
- Enhancing the Power of OOD Detection via Sample-Aware Model Selection (CVPR 2024 · similarity 0.86)
- OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable? (ICML 2025 · similarity 0.86)
- Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection (NeurIPS 2024 · similarity 0.85)
- Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail (AAAI 2025 · similarity 0.85)
- EAT: Towards Long-Tailed Out-of-Distribution Detection (AAAI 2024 · similarity 0.85)
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.
