| fine-grained-image-classification-on-caltech | SE-ResNet-101 (SAP) | – | Top-1 Error Rate: 15.949% |
| fine-grained-image-classification-on-oxford-2 | SE-ResNet-101 (SAP) | – | Accuracy: 86.011 |
| image-classification-on-cifar-10 | ResNet-110 (SAP) | – | Percentage correct: 93.861 |
| image-classification-on-cifar-100 | ResNet-110 (SAP) | – | Percentage correct: 72.537 |
| image-classification-on-stanford-cars | SE-ResNet-101 (SAP) | – | Accuracy: 85.812 |
| object-detection-on-coco-2017 | DyHead (SAP) | – | AP: 42.1AP50: 59.4AP75: 45.9 |
| semantic-segmentation-on-isprs-potsdam | PSPNet (SAP) | – | Overall Accuracy: 88.56Mean IoU: 74.3 |
| semantic-segmentation-on-isprs-vaihingen | UPerNet (SAP) | – | Overall Accuracy: 90.14Category mIoU: 73.27 |