Image Classification on Average (14 datasets)
71.7AccuracyInMaP + ZLaP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| InMaP + ZLaPBackbone=ViT-B/16, Evaluation Protocol=Transductive Zero-Shot2024.04 | 71.7 | 1 | |
| InMaPBackbone=ViT-B/16, Evaluation Protocol=Transductive Zero-Shot2024.04 | 70.7 | — | |
| CLIP + ZLaPBackbone=ViT-B/16, Evaluation Protocol=Transductive Zero-Shot2024.04 | 68.9 | 2.1 | |
| CLIP-DNBackbone=ViT-B/16, Evaluation Protocol=Transductive Zero-Shot2024.04 | 67.3 | — | |
| CLIPBackbone=ViT-B/16, Evaluation Protocol=Transductive Zero-Shot2024.04 | 66.8 | — | |
| TPTBackbone=ViT-B/16, Evaluation Protocol=Transductive Zero-Shot2024.04 | 65.5 | — | |
| InMaP + ZLaPBackbone=ResNet-50, Evaluation Protocol=Transductive Zero-Shot2024.04 | 61.3 | 0.9 | |
| InMaPBackbone=ResNet-50, Evaluation Protocol=Transductive Zero-Shot2024.04 | 60.4 | — | |
| CLIP + ZLaPBackbone=ResNet-50, Evaluation Protocol=Transductive Zero-Shot2024.04 | 60 | 3.4 | |
| TPTBackbone=ResNet-50, Evaluation Protocol=Transductive Zero-Shot2024.04 | 58.8 | — | |
| CLIP-DNBackbone=ResNet-50, Evaluation Protocol=Transductive Zero-Shot2024.04 | 57.3 | — | |
| CLIPBackbone=ResNet-50, Evaluation Protocol=Transductive Zero-Shot2024.04 | 56.6 | — |