Classification on Pets
93.5AccuracyOpenAI-CLIP ViT-L
Evaluation results
| Method | Links | ||
|---|---|---|---|
| OpenAI-CLIP ViT-LN=400M, Zero-shot=true2024.09 | 93.5 | — | |
| Supervised-INArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.06 | 92.1 | — | |
| DINOv2-ARLN=20M, Zero-shot=true2024.09 | 92.1 | — | |
| BYOLArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.06 | 91.7 | — | |
| DINOv2-MpNetN=20M, Zero-shot=true2024.09 | 91.7 | — | |
| Supervised-INArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.06 | 91.5 | — | |
| LAION-CLIP ViT-LN=400M, Zero-shot=true2024.09 | 91.5 | — | |
| BYOLArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.06 | 90.4 | — | |
| SimCLR (repro)Architecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.06 | 89.4 | — | |
| SimCLRArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.06 | 89.2 | — | |
| SimCLR (repro)Architecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.06 | 84.6 | — | |
| SimCLRArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Linear evaluation2020.06 | 83.6 | — | |
| LiT L16LN=112M, Zero-shot=true2024.09 | 83.3 | — | |
| Random initArchitecture=ResNet-50, Pre-training Dataset=ImageNet, Evaluation Protocol=Fine-tuned2020.06 | 81.5 | — | |
| xCLIPBackbone=ViT-B/16, Pre-trained on=IT35M, Mode=Zero-shot2022.10 | 57.1 | — | |
| CLIPBackbone=ViT-B/16, Pre-trained on=IT35M, Mode=Zero-shot2022.10 | 54.7 | — | |
| FLVMIAAlignment=frozen pretrained DINOv2 and GTE-1.5, Setting=Zero-shot2026.05 | 15.97 | — | |
| FLQMIAAlignment=frozen pretrained DINOv2 and GTE-1.5, Setting=Zero-shot2026.05 | 15.1 | — | |
| nCLIPBackbone=ViT-B/16, Pre-trained on=IT35M, Mode=Zero-shot2022.10 | 14.6 | — | |
| SAIL w/ SigLIPAlignment=frozen pretrained DINOv2 and GTE-1.5, Loss=SigLIP, Setting=Zero-shot2026.05 | 14.58 | — | |
| SAIL w/ CLIPAlignment=frozen pretrained DINOv2 and GTE-1.5, Loss=InfoNCE, Setting=Zero-shot2026.05 | 14.06 | — | |
| CSAAlignment=frozen pretrained DINOv2 and GTE-1.5, Setting=Zero-shot2026.05 | 12.56 | — | |
| LiTDA-baseN=0.5M, Zero-shot=true2024.09 | 7.2 | — | |
| LiTLwA-baseN=0.5M, Zero-shot=true2024.09 | 4.8 | — | |
| CLIPPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | — | 92 | |
| FLAIRBackbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | — | 25.9 | |
| ITOPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | — | 91.1 | |
| ITO sub2Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | — | 29.9 | |
| ITO sub2Pre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | — | 90.8 | |
| ITO sub3Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | — | 30.2 |