| Benchmark | Model | Rank | Results |
|---|---|---|---|
| self-supervised-image-classification-on-imagenet-finetuned | CAE (ViT-L/16) | #15 | Top 1 Accuracy: 86.3%Number of Params: 307M |
| semantic-segmentation-on-ade20k | CAE (ViT-L, UperNet) | #57 | Validation mIoU: 54.7 |
| object-detection-on-coco-val2017 | CAE* (ViT-L, 1600ep, Mask R-CNN 1x) | #118 | box AP: 54.5AP50: 75.2AP75: 60.1 |