Object Detection on COCO 50% sampling ratio
40.41AP BoxRILS
Evaluation results
| Method | Links | |
|---|---|---|
| RILSVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 40.41 | |
| MAE+CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 39.24 | |
| CLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 38.5 | |
| MAEVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 38.1 | |
| SLIPVision Encoder=ViT-B/16, Pre-training Dataset=L-20M, Pre-training Epochs=25, Fine-tuning Epochs=122023.01 | 37.73 |