Image Classification on ImageNet-R OOD (test)
31.89Top-1 AccuracySS-CA
Evaluation results
| Method | Links | |
|---|---|---|
| SS-CABackbone=CLIP (ViT /32b), Evaluation Protocol=Linear Probing2025.11 | 31.89 | |
| Chen et al.Backbone=CLIP (ViT /32b), Evaluation Protocol=Linear Probing2025.11 | 31.69 | |
| Xiao et al.Backbone=CLIP (ViT /32b), Evaluation Protocol=Linear Probing2025.11 | 31.65 | |
| Conventional TrainingBackbone=CLIP (ViT /32b), Evaluation Protocol=Linear Probing2025.11 | 31.63 |