| domain-generalization-on-imagenet-a | MAE (ViT-H, 448) | #5 | Top-1 accuracy %: 76.7 |
| domain-generalization-on-imagenet-c | MAE (ViT-H) | #6 | mean Corruption Error (mCE): 33.8Number of params: 632M |
| domain-generalization-on-imagenet-r | MAE (ViT-H, 448) | #9 | Top-1 Error Rate: 33.5 |
| domain-generalization-on-imagenet-sketch | MAE (ViT-H, 448) | #9 | Top-1 accuracy: 50.9 |
| image-classification-on-imagenet | MAE (ViT-H, 448) | #67 | Top 1 Accuracy: 87.8%Number of params: 656M |
| image-classification-on-imagenet | MAE (ViT-H) | #113 | Top 1 Accuracy: 86.9% |
| image-classification-on-imagenet | MAE (ViT-L) | #182 | Top 1 Accuracy: 85.9% |
| image-classification-on-imagenet | MAE (ViT-L) | #402 | Top 1 Accuracy: 83.6% |
| image-classification-on-inaturalist | MAE (ViT-H, 448) | #3 | Top 1 Accuracy: 83.4 |
| image-classification-on-inaturalist-2018 | MAE (ViT-H, 448) | #5 | Top-1 Accuracy: 86.8% |
| image-classification-on-inaturalist-2019 | MAE (ViT-H, 448) | #2 | Top-1 Accuracy: 88.3 |
| image-classification-on-omnibenchmark | MAE | #21 | Average Top-1 Accuracy: 30.6 |
| image-classification-on-places205 | MAE (ViT-H, 448) | #5 | Top 1 Accuracy: 66.8 |
| image-classification-on-places365-standard | MAE (ViT-H, 448) | #3 | Top 1 Accuracy: 60.3 |
| object-detection-on-coco-minival | MAE (ViT-L, Mask R-CNN) | #61 | box AP: 53.3 |
| object-detection-on-coco-minival | MAE (ViT-B, Mask R-CNN) | #79 | box AP: 50.3 |
| self-supervised-image-classification-on-1 | MAE (ViT-H/14, 448) | #7 | Top 1 Accuracy: 87.8%Number of Params: 632M |
| self-supervised-image-classification-on-1 | MAE (ViT-H/14) | #11 | Top 1 Accuracy: 86.9% |
| self-supervised-image-classification-on-imagenet | MAE (ViT-H) | #54 | Top 1 Accuracy: 76.6%Number of Params: 700M |
| self-supervised-image-classification-on-imagenet | MAE (ViT-L) | #61 | Top 1 Accuracy: 75.8%Number of Params: 306M |
| self-supervised-image-classification-on-imagenet | MAE (ViT-B) | #100 | Top 1 Accuracy: 68.0%Number of Params: 80M |
| semantic-segmentation-on-ade20k | MAE (ViT-L, UperNet) | #75 | Validation mIoU: 53.6 |
| semantic-segmentation-on-ade20k | MAE (ViT-B, UperNet) | #149 | Validation mIoU: 48.1 |
| semantic-segmentation-on-imagenet-s | MAE (ViT-B/16, 224x224, SSL+FT, mmseg) | #4 | mIoU (val): 61.6mIoU (test): 61.2 |
| semantic-segmentation-on-imagenet-s | MAE (ViT-B/16, 224x224, SSL+FT) | #5 | mIoU (val): 61.0mIoU (test): 60.2 |
| semantic-segmentation-on-imagenet-s | MAE (ViT-B/16, 224x224, SSL, mmseg) | #17 | mIoU (val): 40.0mIoU (test): 40.3 |
| semantic-segmentation-on-imagenet-s | MAE (ViT-B/16, 224x224, SSL) | #18 | mIoU (val): 38.3mIoU (test): 37.0 |