Object Detection on COCO 5% sampling ratio
16.94AP (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 | 16.94 | |
| MAEVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 15.76 | |
| CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 14.98 | |
| MAE+CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 14.33 | |
| SLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 13.84 |