Research map / Label-efficient and robust learning / OOD and anomaly detection
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Julian Bitterwolf, Alexander Meinke, Maximilian Augustin, Matthias Hein
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 |
|---|---|---|---|
| combine a shared in/out discriminator with the classifier using s2 | Shared Combi · CIFAR-10; test OOD datasets | Mean FPR@95%TPR: 29.34 -> 16.00 | Improved |
| combine a shared in/out discriminator with the classifier using s2 | Shared Combi · CIFAR-100; test OOD datasets | Mean FPR@95%TPR: 67.23 -> 33.01 | Improved |
| use a shared representation for the classifier and discriminator instead of separate representations (ablation) | classifier plus binary discriminator · CIFAR-10; test OOD datasets | Mean FPR@95%TPR: 21.40 -> 16.06 | Improved |
| use a shared representation for the classifier and discriminator instead of separate representations (ablation) | classifier plus binary discriminator · CIFAR-100; test OOD datasets | Mean FPR@95%TPR: 41.94 -> 33.06 | Improved |
| use a shared-trained discriminator with the separately trained plain classifier (ablation) | Plain × Sha Disc · CIFAR-10; test OOD datasets | Mean FPR@95%TPR: 21.40 -> 15.96 | Improved |
| use a shared-trained discriminator with the separately trained plain classifier (ablation) | Plain × Sha Disc · CIFAR-100; test OOD datasets | Mean FPR@95%TPR: 41.94 -> 33.38 | Improved |
| use s2 rather than s1 to score the background-class model (ablation) | BGC · CIFAR-10; test OOD datasets | Mean FPR@95%TPR: 18.83 -> 16.52 | Improved |
| use s2 rather than s3 to score the shared combination (ablation) | Shared Combi · CIFAR-10; test OOD datasets | Mean FPR@95%TPR: 16.06 -> 16.00 | No clear effect |
| use s2 rather than s3 to score the shared combination (ablation) | Shared Combi · CIFAR-100; test OOD datasets | Mean FPR@95%TPR: 33.06 -> 33.01 | No clear effect |
| train the binary discriminator against uniform noise instead of a diverse surrogate OOD set | BinDisc Uniform · CIFAR-10 vs. unseen OOD datasets | Mean AUC: 57.97 -> 45.90 | Hurt |
| use shared training with a discriminator rather than plain classifier training (ablation) | Shared Classi · CIFAR-10; test OOD datasets | Mean FPR@95%TPR: 53.01 -> 29.34 | Improved |
Closest papers by meaning
- Mining In-distribution Attributes in Outliers for Out-of-distribution Detection (AAAI 2025 · similarity 0.92)
- Test-Time Linear Out-of-Distribution Detection (CVPR 2024 · similarity 0.92)
- Learning to Shape In-distribution Feature Space for Out-of-distribution Detection (NeurIPS 2024 · similarity 0.91)
- Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation (NeurIPS 2024 · similarity 0.91)
- What If the Input is Expanded in OOD Detection? (NeurIPS 2024 · similarity 0.91)
- Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection (NeurIPS 2024 · similarity 0.91)
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.
