Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Placeholders for Open-Set Recognition
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use ProSER instead of GFROSR | Open-set detection · CIFAR10 | AUC: 83.1 -> 89.1 | Helped |
| Use ProSER instead of GFROSR | Open-set detection · CIFAR+10 | AUC: 91.5 -> 96.0 | Helped |
| Use ProSER instead of GFROSR | Open-set detection · CIFAR+50 | AUC: 91.3 -> 95.3 | Helped |
| Use ProSER instead of GFROSR | Open-set detection · Tiny-ImageNet | AUC: 64.7 -> 69.3 | Helped |
| Use ProSER instead of GFROSR | Open-set recognition · CIFAR10 + ImageNet-crop | macro F1: 75.7 -> 84.9 | Helped |
| Use ProSER instead of GFROSR | Open-set recognition · CIFAR10 + ImageNet-resize | macro F1: 79.2 -> 82.4 | Helped |
| Use ProSER instead of GFROSR | Open-set recognition · CIFAR10 + LSUN-crop | macro F1: 75.1 -> 86.7 | Helped |
| Use ProSER instead of GFROSR | Open-set recognition · CIFAR10 + LSUN-resize | macro F1: 80.5 -> 85.6 | Helped |
| Add manifold mixup data placeholders (ablation) | Plain CNN open-set recognition · CIFAR100, varying openness | macro F1 | Helped |
| Add classifier dummy placeholders (ablation) | Plain CNN open-set recognition · CIFAR100, varying openness | macro F1 | Helped |
| Combine data and classifier placeholders (ablation) | Plain CNN open-set recognition · CIFAR100, varying openness | macro F1 | Helped |
| Use multiple dummy classifiers rather than one (ablation) | ProSER · CIFAR100, varying openness | macro F1 | Helped |
Closest papers by meaning
- Open-Set Recognition: A Good Closed-Set Classifier is All You Need (ICLR 2022 · similarity 0.88)
- All Beings Are Equal in Open Set Recognition (AAAI 2024 · similarity 0.86)
- From Coarse to Fine-Grained Open-Set Recognition (CVPR 2024 · similarity 0.84)
- Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition (AAAI 2025 · similarity 0.84)
- Frequency Shuffling and Enhancement for Open Set Recognition (AAAI 2024 · similarity 0.83)
- Exploring Diverse Representations for Open Set Recognition (AAAI 2024 · similarity 0.83)
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.