Object Detection on COCO 2% sampling ratio
6.46AP (Box)RILS
Evaluation results
| Method | Links | |
|---|---|---|
| RILSVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 6.46 | |
| MAEVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 6.1 | |
| MAE+CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 5.28 | |
| CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 5.05 | |
| SLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 4.54 |