Image Classification on Pets37
93.8AccuracyViT-12/16
Evaluation results
| Method | Links | |
|---|---|---|
| ViT-12/16Architecture=ViT-12/16, Pre-training Dataset=ImageNet-1K (1.3M), Evaluation Protocol=Fine-tuned2025.02 | 93.8 | |
| ViT-12/16Architecture=ViT-12/16, Pre-training Dataset=ImageNet-21K (14.2M), Evaluation Protocol=Fine-tuned2025.02 | 93.2 | |
| SCOTT-12/16Architecture=SCOTT-12/16, Pre-training Dataset=Target dataset (unlabeled), Evaluation Protocol=Frozen, Training Epochs=12002025.02 | 90.7 | |
| CLIPModel Type=Teacher, Img. Enc.=ViT-B/16, Param. Size=76M, zero-shot=true2023.01 | 88.9 | |
| SCOTT-7/16Architecture=SCOTT-7/16, Pre-training Dataset=Target dataset (unlabeled), Evaluation Protocol=Frozen, Training Epochs=12002025.02 | 88 | |
| BeamCLIPModel Type=Student, Img. Enc.=RN50, Param. Size=24M2023.01 | 86.94 | |
| SCOTT-12/16Architecture=SCOTT-12/16, Pre-training Dataset=Target dataset (unlabeled), Evaluation Protocol=Frozen2025.02 | 86.2 | |
| SCOTT-7/16Architecture=SCOTT-7/16, Pre-training Dataset=Target dataset (unlabeled), Evaluation Protocol=Frozen2025.02 | 81.6 | |
| KDModel Type=Student, Img. Enc.=RN50, Param. Size=24M2023.01 | 77.51 | |
| CRDModel Type=Student, Img. Enc.=RN50, Param. Size=24M2023.01 | 62.22 |