Research map / Label-efficient and robust learning / OOD and anomaly detection
Meta OOD Learning For Continuously Adaptive OOD Detection
Xinheng Wu, Jie Lu, Zhen Fang, Guangquan Zhang
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 uncertainty regularization L_ood with virtual OOD samples (ablation) | MOL · R-MNIST | AUROC (R-NOTMNIST): 94.1 -> 96.5 | Improved |
| add distribution discrepancy constraint L_qry in outer loop (ablation) | MOL · R-MNIST | ID accuracy: 32.2 -> 35.6 | Improved |
| start L_ood earlier in training (E=1/3 instead of 2/3) (ablation) | MOL · R-MNIST | ID accuracy: 35.6 -> 28.7 | Hurt |
| start L_ood later in training (E=4/5 instead of 2/3) (ablation) | MOL · R-MNIST | AUROC (R-Cifar10bw): 98.9 -> 95.2 | Hurt |
| use random sampled test trajectories instead of fixed (ablation) | MOL · R-MNIST | AUROC (R-NOTMNIST): 97.9 -> 97.7 ± 0.4 | No clear effect |
| fine-tune classifier at test time (Simple Adaptive) for static OOD baselines | static OOD baselines · R-MNIST | ID accuracy / FPR95: around 2.7% ID accuracy gain; FPR95 reduced 5.3% to 19.3% | Improved |
| train baselines with domain adaptation (DAN) using all shifting training samples | static OOD baselines · R-MNIST | AUROC: AUROC dropped 17.9% to 26.3% | Hurt |
| MOL versus best static baselines with adaptation | MOL · Cifar10C | average AUROC: 66.4 -> 70.6 | Improved |
| MOL versus Gram on R-MNIST FPR95 | MOL · R-MNIST | average FPR95: 7.6 vs 11.5 | Hurt |
Closest papers by meaning
- OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary (CVPR 2025 · similarity 0.91)
- Test-Time Linear Out-of-Distribution Detection (CVPR 2024 · similarity 0.90)
- Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection (NeurIPS 2024 · similarity 0.89)
- Enhancing the Power of OOD Detection via Sample-Aware Model Selection (CVPR 2024 · similarity 0.89)
- Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection (CVPR 2025 · similarity 0.89)
- What If the Input is Expanded in OOD Detection? (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.
