| image-classification-on-gashissdb | Res2Net-50 | #2 | Accuracy: 98.68Precision: 99.91F1-Score: 99.29 |
| medical-image-classification-on-nct-crc-he-100k | Res2Net-50 | #6 | Accuracy (%): 93.37F1-Score: 96.25Precision: 99.93… |
| salient-object-detection-on-pascal-s | DSS (Res2Net-50) | #7 | F-measure: 0.841MAE: 0.099 |
| salient-object-detection-on-ecssd | DSS (Res2Net-50) | #8 | F-measure: 0.926MAE: 0.056 |
| salient-object-detection-on-hku-is | DSS (Res2Net-50) | #9 | F-measure: 0.905MAE: 0.05 |
| semantic-segmentation-on-pascal-voc-2012-val | Deeplab v3+ (Res2Net-101) | #10 | mIoU: 79.3% |
| salient-object-detection-on-dut-omron | DSS (Res2Net-50) | #13 | F-measure: 0.800MAE: 0.071 |
| instance-segmentation-on-coco-minival | Res2Net-101+HTC | #82 | mask AP: 41.3 |
| instance-segmentation-on-coco-minival | Faster R-CNN (Res2Net-50) | #109 | mask AP: 35.6AP50: 57.6APL: 53.7APM: 37.9APS: 15.7 |
| image-classification-on-cifar-100 | Res2NeXt-29 | #114 | Percentage correct: 83.44 |
| object-detection-on-coco-val2017 | Faster R-CNN (Res2Net-50) | #439 | box AP: 33.7AP50: 53.6APS: 14APM: 38.3APL: 51.1 |
| image-classification-on-imagenet | Res2Net-101 | #693 | Top 1 Accuracy: 81.23% |
| image-classification-on-imagenet | Res2Net-50-299 | #862 | Top 1 Accuracy: 78.59% |