Research map / Label-efficient and robust learning / OOD and anomaly detection
Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
Read the paperCheck 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 |
|---|---|---|---|
| Generate candidate unseen labels per image and score their accumulated CLIP probability, instead of using maximum softmax probability | CLIP zero-shot OOD detection · CIFAR10 | AUROC: 88.0\stdv3.3 -> 93.0\stdv1.7 | Helped |
| Generate candidate unseen labels per image and score their accumulated CLIP probability, instead of using maximum softmax probability | CLIP zero-shot OOD detection · CIFAR100 | AUROC: 78.1\stdv3.1 -> 82.1\stdv2.1 | Helped |
| Generate candidate unseen labels per image and score their accumulated CLIP probability, instead of using maximum softmax probability | CLIP zero-shot OOD detection · CIFAR+10 | AUROC: 94.9\stdv0.8 -> 97.8\stdv0.6 | Helped |
| Generate candidate unseen labels per image and score their accumulated CLIP probability, instead of using maximum softmax probability | CLIP zero-shot OOD detection · CIFAR+50 | AUROC: 95.0\stdv0.0 -> 97.6\stdv0.0 | Helped |
| Generate candidate unseen labels per image and score their accumulated CLIP probability, instead of using maximum softmax probability | CLIP zero-shot OOD detection · TinyImageNet | AUROC: 80.4\stdv2.5 -> 84.6\stdv1.0 | Helped |
Closest papers by meaning
- ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection (CVPR 2024 · similarity 0.89)
- Learning with Mixture of Prototypes for Out-of-Distribution Detection (ICLR 2024 · similarity 0.88)
- Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection (ICML 2024 · similarity 0.88)
- Learning Transferable Negative Prompts for Out-of-Distribution Detection (CVPR 2024 · similarity 0.87)
- A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise? (CVPR 2024 · similarity 0.87)
- Enhancing the Power of OOD Detection via Sample-Aware Model Selection (CVPR 2024 · similarity 0.87)
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.