Research map / Label-efficient and robust learning / OOD and anomaly detection
Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning
Yang Yang, Yuxuan Zhang, XIN SONG, Yi Xu
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 |
|---|---|---|---|
| replace mu=0.8 weighting with mu=0.2 (ablation) | PAL · CIFAR-100 20% ID | accuracy: 69.4 -> 66.2 | Hurt |
| use mu=1 (informativeness only dominance) instead of 0.8 (ablation) | PAL · CIFAR-100 20% ID | accuracy: 69.4 -> 67.6 | Hurt |
| lower mu from 0.8 to 0.2 for precision (ablation) | PAL · CIFAR-100 20% ID | precision: 25.4 -> 32.4 | Improved |
| use mu=0.8 versus 1 for OOD detection recall (ablation) | PAL · CIFAR-100 20% ID | recall: 69.7 -> 73.8 | Improved |
| replace meta-weight with Coreset (PAL_Core) (ablation) | PAL · CIFAR-100 20% ID | accuracy: 69.4 -> 65.9 | Hurt |
| replace informativeness criterion with MSP (PAL_MSP) (ablation) | PAL · CIFAR-100 20% ID | accuracy: 69.4 -> 64.7 | Hurt |
| replace informativeness criterion with energy score (PAL_energy) (ablation) | PAL · CIFAR-100 20% ID | accuracy: 69.4 -> 66.2 | Hurt |
| replace informativeness criterion with MSP (PAL_MSP) (ablation) | PAL · CIFAR-10 20% ID | accuracy: 98.7 -> 98.0 | Hurt |
| remove representativeness criterion or informativeness criterion (w/o omega, w/o SID) (ablation) | PAL · CIFAR-10, CIFAR-100, Tiny-Imagenet 20% ID | accuracy | Hurt |
| actively query pseudo-OOD instances (PAL) instead of only pseudo-ID (LfOSA) | LfOSA · Tiny-Imagenet 20% ID | accuracy: 47.9 -> 52.1 | Improved |
| actively query pseudo-OOD instances (PAL) instead of only pseudo-ID (LfOSA) | LfOSA · CIFAR-100 20% ID | accuracy: 66.1 -> 69.4 | Improved |
| actively query pseudo-OOD instances (PAL) instead of only pseudo-ID (LfOSA) | LfOSA · CIFAR-10 20% ID, round 1 | accuracy: 84.2 -> 91.1 | Improved |
Closest papers by meaning
- Active Sampling for Open-Set Classification without Initial Annotation (AAAI 2019 · similarity 0.89)
- Joint Out-of-Distribution Filtering and Data Discovery Active Learning (CVPR 2025 · similarity 0.88)
- Active Learning for Open-Set Annotation (CVPR 2022 · similarity 0.88)
- Inconsistency-Based Data-Centric Active Open-Set Annotation (AAAI 2024 · similarity 0.87)
- Instance-wise Supervision-level Optimization in Active Learning (CVPR 2025 · similarity 0.87)
- Entropic Open-Set Active Learning (AAAI 2024 · similarity 0.85)
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.
