Object Detection on COCO 20% sampling ratio
31.97AP (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 | 31.97 | |
| MAE+CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 29.99 | |
| CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 29.88 | |
| MAEVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 29.78 | |
| SLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 29.53 |