Image Classification on Carton
6Carton GapMAE+LLE
Evaluation results
| Method | Links | |
|---|---|---|
| MAE+LLEBackbone=ViT-B/16, Evaluation Protocol=Fine-tuned2022.12 | 6 | |
| SWAGBackbone=ViT-L/16, Evaluation Protocol=Linear Probing, Pre-training Dataset=IG-3.6B2022.12 | 6 | |
| SWAGtrain data=IG-3.6B, evaluation protocol=linear probing, backbone=ViT-H2022.12 | 8 | |
| CLIPBackbone=ViT-L/16, Evaluation Protocol=Zero-shot, Pre-training Dataset=WIT2022.12 | 12 | |
| CLIPBackbone=ViT-L/16, Evaluation Protocol=Zero-shot, Pre-training Dataset=LAION2022.12 | 12 | |
| MAE+LLEBackbone=ViT-L/16, Evaluation Protocol=Fine-tuned2022.12 | 12 | |
| Greedy SoupBackbone=ViT-B/32, Evaluation Protocol=Fine-tuned, Pre-training Dataset=WIT2022.12 | 16 | |
| CLIPtrain data=LAION-2B, evaluation protocol=zero-shot, backbone=ViT-H2022.12 | 16 | |
| SEERBackbone=RG-32gf, Evaluation Protocol=Fine-tuned, Pre-training Dataset=IG-1B2022.12 | 18 | |
| SWAGBackbone=ViT-B/16, Evaluation Protocol=Linear Probing, Pre-training Dataset=IG-3.6B2022.12 | 18 | |
| SWAGtrain data=IG-3.6B, evaluation protocol=fine-tuning, backbone=ViT-H2022.12 | 18 | |
| SWAGBackbone=ViT-L/16, Evaluation Protocol=Fine-tuned, Pre-training Dataset=IG-3.6B2022.12 | 20 | |
| MoCov3Backbone=ViT-B/16, Evaluation Protocol=Linear Probing2022.12 | 22 | |
| MAEBackbone=ViT-L/16, Evaluation Protocol=Fine-tuned2022.12 | 22 | |
| Uniform SoupBackbone=ViT-B/32, Evaluation Protocol=Fine-tuned, Pre-training Dataset=WIT2022.12 | 24 | |
| SWAGBackbone=ViT-B/16, Evaluation Protocol=Fine-tuned, Pre-training Dataset=IG-3.6B2022.12 | 24 | |
| MAEBackbone=ViT-B/16, Evaluation Protocol=Fine-tuned2022.12 | 24 | |
| ERMBackbone=ViT-B/162022.12 | 26 | |
| MAE+LLEtrain data=IN-1k, evaluation protocol=Last Layer Ensemble, backbone=ViT-H2022.12 | 28 | |
| MAEtrain data=IN-1k, evaluation protocol=fine-tuning, backbone=ViT-H2022.12 | 30 | |
| ERMBackbone=RG-32gf2022.12 | 32 | |
| ERMBackbone=ViT-B/322022.12 | 34 | |
| ERMBackbone=ViT-L/162022.12 | 34 |