Research map / Label-efficient and robust learning / OOD and anomaly detection
STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data
Zhi Zhou, Lan-Zhe Guo, Zhanzhan Cheng, Yu-Feng Li, Shiliang Pu
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 Structure-Keep loss to unzipping (vs unzipping without it) (ablation) | STEP · CIFAR-10 vs TINr / LSUNr | AUROC: 79.58 -> 95.62 (TINr); 80.38 -> 99.07 (LSUNr) | Improved |
| use projected detection-specific space (STEP) vs plain Mahalanobis distance (ablation) | STEP · CIFAR-10 vs TINr / LSUNr | AUROC: 90.96 -> 95.62 (TINr); 93.46 -> 99.07 (LSUNr) | Improved |
| add KNN-based geodesic distance to Mahalanobis (ablation) | MAH · CIFAR-10 vs TINr / LSUNr | AUROC: 90.96 -> 91.26 (TINr); 93.46 -> 97.35 (LSUNr) | Mixed |
| STEP vs UOOD† (uses OOD validation set) | STEP · CIFAR-100 vs TINr, LSUNr | AUROC: 95.31 -> 93.51 (TINr); 98.96 -> 98.20 (LSUNr) | Hurt |
| STEP vs UOOD† on CIFAR-10 benchmarks | STEP · CIFAR-10 vs TINr | AUROC: 92.63 -> 95.61 | Improved |
| train with known OOD set then test on unknown OOD set | UOOD† and MAH† · CIFAR-10 known vs unknown OOD | AUROC | Hurt |
| train with known OOD set then test on unknown OOD set | STEP · CIFAR-10 known vs unknown OOD | AUROC | No clear effect |
| vary KNN neighbors K from 2 to 18 (ablation) | STEP · various OOD sets | AUROC | No clear effect |
Closest papers by meaning
- Can We Ignore Labels in Out of Distribution Detection? (ICLR 2025 · similarity 0.90)
- EAT: Towards Long-Tailed Out-of-Distribution Detection (AAAI 2024 · similarity 0.90)
- How Does Unlabeled Data Provably Help Out-of-Distribution Detection? (ICLR 2024 · similarity 0.90)
- When and How Does In-Distribution Label Help Out-of-Distribution Detection? (ICML 2024 · similarity 0.89)
- Image Background Serves as Good Proxy for Out-of-distribution Data (ICLR 2024 · similarity 0.89)
- Learning with Mixture of Prototypes for Out-of-Distribution Detection (ICLR 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.
