Research map / Label-efficient and robust learning / OOD and anomaly detection
Self-Supervised Learning for Generalizable Out-of-Distribution Detection
Sina Mohseni, Mandar Pitale, JBS Yadawa, Zhangyang Wang
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 self-supervised reject-class head trained on unlabeled OOD data instead of OE calibration | WRN classifier · CIFAR-100 (avg 5 OOD sets) | AUROC: +6.89% | Improved |
| same, vs OE | WRN classifier · CIFAR-10 (avg 5 OOD sets) | AUROC: +1.80% | Improved |
| same, vs OE | classifier · SVHN / MNIST | AUROC: +0.21% / +1.29% | Improved |
| evaluate on mixture of OOD distributions | ODIN / Mahalanobis (tuned on target OOD) · CIFAR-100 | AUROC: -14.07% (ODIN), -25.84% (Mahalanobis) | Hurt |
| use ImageNet-22k instead of Tiny Images as OOD training set (ablation) | Ours · CIFAR-10 | AUROC: 97.37% -> 90.40% | Hurt |
| blend ImageNet OOD samples with in-distribution images (alpha 0.1) (ablation) | Ours with ImageNet OOD · CIFAR-10 | AUROC: 90.40% -> 91.72% | Improved |
| vary number of reject classes k (ablation) | Ours · CIFAR-10 | AUROC: std 0.31% | No clear effect |
| vary number of reject classes k (ablation) | Ours · CIFAR-100 | AUROC: std 5.40% | Mixed |
| use alternative OOD scores (sum, entropy) instead of max softmax of reject classes (ablation) | Ours · CIFAR-10/100 mixed OOD | AUROC: 97.77 -> 97.88 (entropy) | No clear effect |
| use the OOD detector for selective classification | WRN classifier · CIFAR-100 | normal classification error: -11.81% | Improved |
| Ours vs Deep SVDD | one-class classification · CIFAR-10 | AUROC: 64.81% -> 77.75% | Improved |
Closest papers by meaning
- Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers (ECCV 2018 · similarity 0.90)
- Can We Ignore Labels in Out of Distribution Detection? (ICLR 2025 · similarity 0.89)
- Generalized Out-of-Distribution Detection: A Survey (IJCV 2024 · similarity 0.89)
- Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation (ICML 2025 · similarity 0.88)
- A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks (ICLR 2022 · similarity 0.88)
- Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection (CVPR 2025 · similarity 0.86)
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.
