Research map / Label-efficient and robust learning / OOD and anomaly detection
Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 informative extrapolation of part of the auxiliary outliers | OE · CIFAR-10 | FPR95: 13.76$\pm$0.23 -> 11.66$\pm$0.04 | Helped |
| Add informative extrapolation of part of the auxiliary outliers | OE · CIFAR-100 | FPR95: 27.67$\pm$0.43 -> 24.80$\pm$0.51 | Helped |
| Add informative extrapolation of part of the auxiliary outliers | OE · ImageNet | FPR95: 61.94$\pm$0.03 -> 60.12$\pm$0.11 | Helped |
| Extrapolate the full outlier batch rather than only a portion (ablation) | DivOE · CIFAR-100 | FPR95: 24.80 -> 43.18 | Hurt |
| Extrapolate the full outlier batch rather than only a portion (ablation) | DivOE · CIFAR-10 | FPR95: 11.66 -> 22.05 | Hurt |
| Add DivOE extrapolation | Energy (w. auxiliary outliers) · CIFAR-10 | FPR95: 18.15$\pm$0.32 -> 16.03$\pm$0.35 | Helped |
| Add DivOE extrapolation | NTOM · CIFAR-100 | FPR95: 27.58$\pm$0.88 -> 25.97$\pm$0.74 | Helped |
| Add DivOE extrapolation | POEM · CIFAR-10 | FPR95: 17.81$\pm$0.78 -> 15.22$\pm$0.20 | Helped |
| Add DivOE extrapolation | DOE · CIFAR-100 | FPR95: 30.69$\pm$0.93 -> 20.26$\pm$0.20 | Helped |
| Use an excessively large extrapolation strength (ablation) | DivOE · OOD detection benchmarks | FPR95 | Hurt |
Closest papers by meaning
- Out-Of-Distribution Detection with Diversification (Provably) (NeurIPS 2024 · similarity 0.92)
- DOS: Diverse Outlier Sampling for Out-of-Distribution Detection (ICLR 2024 · similarity 0.91)
- Mining In-distribution Attributes in Outliers for Out-of-distribution Detection (AAAI 2025 · similarity 0.89)
- Out-of-Distribution Detection with Prototypical Outlier Proxy (AAAI 2025 · similarity 0.89)
- Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection (NeurIPS 2024 · similarity 0.89)
- Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation (NeurIPS 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.