| frozen-feature-label-propagation-on-davis-2017-val | DINO (ViT-B/8) | #2 | J&F: 71.4 |
| visual-place-recognition-on-hawkins | DINO | #2 | Recall@1: 46.61 |
| visual-place-recognition-on-laurel-caverns | DINO | #2 | Recall@1: 41.07 |
| visual-place-recognition-on-mid-atlantic-ridge | DINO | #2 | Recall@1: 27.72 |
| visual-place-recognition-on-gardens-point | DINO | #3 | Recall@1: 78.50 |
| visual-place-recognition-on-nardo-air | DINO | #3 | Recall@1: 57.75 |
| video-object-segmentation-on-davis-2017 | DINO (ViT-B/8, ImageNet retrain) | #4 | J&F: 71.4 |
| visual-place-recognition-on-17-places | DINO | #4 | Recall@1: 61.82 |
| visual-place-recognition-on-nardo-air-r | DINO | #4 | Recall@1: 84.51 |
| visual-place-recognition-on-vp-air | DINO | #4 | Recall@1: 24.02 |
| visual-place-recognition-on-oxford-robotcar | DINO | #7 | Recall@1: 15.71 |
| image-classification-on-omnibenchmark | DINO | #8 | Average Top-1 Accuracy: 38.9 |
| visual-place-recognition-on-baidu-mall | DINO | #8 | Recall@1: 48.30 |
| image-retrieval-on-rparis-hard | Dino | #13 | mAP: 51.6 |
| image-retrieval-on-rparis-medium | Dino | #13 | mAP: 75.3 |
| visual-place-recognition-on-st-lucia | DINO | #17 | Recall@1: 45.22 |
| image-retrieval-on-roxford-hard | Dino | #19 | mAP: 24.3 |
| image-retrieval-on-roxford-medium | Dino | #19 | mAP: 51.5 |
| self-supervised-image-classification-on-imagenet | DINO (xcit_medium_24_p8) | #22 | Top 1 Accuracy: 80.3%Number of Params: 84M |
| self-supervised-image-classification-on-imagenet | DINO (ViT-B/8) | #24 | Top 1 Accuracy: 80.1%Number of Params: 80M |
| self-supervised-image-classification-on-imagenet | DINO (ViT-S/8) | #29 | Top 1 Accuracy: 79.7%Number of Params: 21M |
| self-supervised-image-classification-on-imagenet | DINO (ViT-B/16) | #42 | Top 1 Accuracy: 78.2%Number of Params: 85M |
| self-supervised-image-classification-on-imagenet | DINO (ViT-S/16) | #52 | Top 1 Accuracy: 77.0%Number of Params: 21M |
| self-supervised-image-classification-on-imagenet | DINO (ResNet-50) | #68 | Top 1 Accuracy: 75.3%Number of Params: 24M |
| visual-place-recognition-on-pittsburgh-30k-test | DINO | #37 | Recall@1: 70.13 |
| self-supervised-image-classification-on-imagenet-finetuned | DINO (ViT-B/16) | #48 | Top 1 Accuracy: 82.8%Number of Params: 85M |
| image-classification-on-imagenet | DINO (ViT-B/8) | #757 | Top 1 Accuracy: 80.1% |