| semantic-segmentation-on-ade20k | DAT-B (UperNet) | #144 | Validation mIoU: 49.38Params (M): 121 |
| semantic-segmentation-on-ade20k | DAT-S (UperNet) | #163 | Validation mIoU: 48.31Params (M): 81 |
| semantic-segmentation-on-ade20k | DAT-T (UperNet) | #203 | Validation mIoU: 45.54Params (M): 60 |
| object-detection-on-coco-val2017 | DAT-S (RetinaNet 3x) | #263 | box AP: 47.9AP50: 69.6AP75: 51.2APS: 32.3APM: 51.8APL: 63.4 |
| image-classification-on-imagenet | DAT-B (384 res, IN-1K only) | #306 | Top 1 Accuracy: 84.8%Number of params: 88MGFLOPs: 49.8 |
| image-classification-on-imagenet | DAT-S | #424 | Top 1 Accuracy: 83.7%Number of params: 50MGFLOPs: 9.0 |
| image-classification-on-imagenet | DAT-T | #620 | Top 1 Accuracy: 82.0%Number of params: 29MGFLOPs: 4.6 |