Crack Segmentation On Khanhha S Dataset 4X 1
評価指標
AHD95
Average IOU
HD95_min
IoU_max
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | AHD95 | Average IOU | HD95_min | IoU_max | Paper Title | Repository |
|---|---|---|---|---|---|---|
| CSBSR (w/ PSPNet+FOW+BlurSkip) | 19.10 | 0.528 | 18.06 | 0.550 | Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images | |
| CSBSR (w/ PSPNet) | 22.52 | 0.552 | 20.92 | 0.573 | Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images | |
| CSSR (w/ PSPNet) | 24.74 | 0.539 | 21.20 | 0.557 | Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution | |
| DSRL | 148.97 | 0.285 | 44.23 | 0.391 | Dual Super-Resolution Learning for Semantic Segmentation | |
| CSBSR (w/ PSPNet+FOW) | 21.70 | 0.551 | 18.73 | 0.573 | Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images | |
| CSBSR (w/ HRNet+OCR) | 20.29 | 0.534 | 17.54 | 0.553 | Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images | |
| SrcNet | 130.47 | 0.320 | 95.16 | 0.368 | Deep super resolution crack network (SrcNet) for improving computer vision–based automated crack detectability in in situ bridges | - |
0 of 7 row(s) selected.