| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-classification-on-imagenet | ResNet-34 (X-volution, stage3) | – | Top 1 Accuracy: 75% |
| image-classification-on-imagenet | ResNet-50 (X-volution, stage3) | – | Top 1 Accuracy: 76.6% |
| instance-segmentation-on-coco-minival | Mask R-CNN (FPN, X-volution, SA) | – | mask AP: 37.2APL: 53.1APM: 40APS: 19.2 |
| object-detection-on-coco-val2017 | Faster R-CNN (FPN, X-volution) | – | box AP: 42.8AP50: 64AP75: 46.4APS: 26.9APM: 46APL: 55 |