OOD Detection on SUN
99.19AUROCLoCoOp (GL-MCM)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LoCoOp (GL-MCM)Learning Setup=CLIP Prompt Learning 16-shot2024.05 | 99.19 | — | — | |
| CLS-MLearning Setup=CLIP Prompt Learning 16-shot, Base Model=Prompt-SRC2024.05 | 98.75 | — | — | |
| CLS-ELearning Setup=CLIP Prompt Learning 16-shot, Base Model=Prompt-SRC2024.05 | 98.27 | — | — | |
| DynProtoBackbone=CLIP-RN502026.04 | 97.95 | — | 9.26 | |
| AdaNegLearning Setup=Non-Prompt-Learning Zero-shot CLIP2024.05 | 97.44 | — | — | |
| MaxLogitLearning Setup=CLIP Prompt Learning 16-shot2024.05 | 97.44 | — | — | |
| CSPBackbone=CLIP-RN502026.04 | 95.78 | — | 18.68 | |
| EnergyLearning Setup=CLIP Prompt Learning 16-shot2024.05 | 95.6 | — | — | |
| NegLabelLearning Setup=Non-Prompt-Learning Zero-shot CLIP2024.05 | 95.49 | — | — | |
| NegLabelBackbone=CLIP-RN502026.04 | 94.56 | — | 26.51 | |
| APEXBackbone=ResNet-50, Evaluation Protocol=fine-tuning, Pre-training=pre-trained, In-Distribution (ID) Dataset=ImageNet-1002026.02 | 93.31 | 41.89 | — | |
| APMBackbone=ResNet-50, Evaluation Protocol=fine-tuning, Pre-training=pre-trained, In-Distribution (ID) Dataset=ImageNet-1002026.02 | 93.28 | 41.96 | — | |
| CIDERBackbone=ResNet-50, Evaluation Protocol=fine-tuning, Pre-training=pre-trained, In-Distribution (ID) Dataset=ImageNet-1002026.02 | 92.84 | 42.26 | — | |
| PALMBackbone=ResNet-50, Evaluation Protocol=fine-tuning, Pre-training=pre-trained, In-Distribution (ID) Dataset=ImageNet-1002026.02 | 92.77 | 43.12 | — | |
| LoCoOpBackbone=CLIP-RN502026.04 | 92.58 | — | 35.27 | |
| kNN+Backbone=ResNet-50, Evaluation Protocol=fine-tuning, Pre-training=pre-trained, In-Distribution (ID) Dataset=ImageNet-1002026.02 | 92.25 | 41.85 | — | |
| MCMLearning Setup=Non-Prompt-Learning Zero-shot CLIP2024.05 | 92.25 | — | — | |
| SCTBackbone=CLIP-RN502026.04 | 91.97 | — | 35.12 | |
| GLMCMBackbone=CLIP-RN502026.04 | 91.24 | — | 39.42 | |
| MCMBackbone=CLIP-RN502026.04 | 90.42 | — | 48.35 |