Research map / Label-efficient and robust learning / OOD and anomaly detection
OpenMix: Exploring Outlier Samples for Misclassification Detection
Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu
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 |
|---|---|---|---|
| Train with OpenMix instead of MSP | WRNet · CIFAR-10 | AUROC: 93.14±0.38 -> 94.81±0.34 | Improved |
| Train with OpenMix instead of MSP | WRNet · CIFAR-100 | AUROC: 88.50±0.44 -> 89.06±0.11 | Improved |
| Add Outlier Exposure | MSP on CIFAR-10 · CIFAR-10 | FPR95: 30.15±1.98 -> 38.78±2.59 | Hurt |
| Add a reject class but omit outlier transformation (ablation) | MSP on ResNet110 · CIFAR-10 | AUROC: 90.13 -> 91.15 | Improved |
| Add outlier transformation with uniform-distribution soft labels, without a reject class (ablation) | MSP on ResNet110 · CIFAR-10 | AUROC: 90.13 -> 87.13 | Hurt |
| Add the reject class and outlier transformation together (ablation) | MSP on ResNet110 · CIFAR-10 | AUROC: 90.13 -> 92.09 | Improved |
| Replace Mixup with CutMix for outlier transformation (ablation) | OpenMix on ResNet110 · CIFAR-10 | AUROC: 92.09±0.36 -> 93.45±0.44 | Improved |
| Replace Mixup with Manifold Mixup for outlier transformation (ablation) | OpenMix on ResNet110 · CIFAR-10 | AURC: 6.31 -> 5.67 | Improved |
| Train with OpenMix | ResNet on CIFAR-10 · CIFAR-10-C | AUROC: 79.92 -> 84.98 | Improved |
Closest papers by meaning
- Out-of-Distribution Detection with Prototypical Outlier Proxy (AAAI 2025 · similarity 0.88)
- How Does Unlabeled Data Provably Help Out-of-Distribution Detection? (ICLR 2024 · similarity 0.88)
- DOS: Diverse Outlier Sampling for Out-of-Distribution Detection (ICLR 2024 · similarity 0.87)
- Out-Of-Distribution Detection with Diversification (Provably) (NeurIPS 2024 · similarity 0.87)
- Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning (AAAI 2024 · similarity 0.86)
- Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection (NeurIPS 2024 · 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.
