Video Polyp Segmentation on SUN-SEG Hard (Unseen)
89.4S Alpha ScoreYOLO-SAM 2
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| YOLO-SAM 22024.09 | 89.4 | — | — | 93.2 | 90.2 | 85.2 | 0.941 | — | — | — | |
| SALIMode=Unseen, Backbone=PVTv22024.06 | 87.4 | — | 79 | 82.2 | 82.2 | 83 | 92 | — | — | — | |
| MASTMode=Unseen2024.06 | 86.1 | — | 77.7 | 81.6 | 80.3 | 81.1 | 91.4 | — | — | — | |
| SLT-NetMode=Unseen2024.06 | 84.4 | — | 75.7 | 79.5 | 78.1 | 76 | 90.4 | — | — | — | |
| SLT-Net2024.09 | 84.4 | — | — | 79.5 | 78.1 | 76 | 0.904 | — | — | — | |
| Temporally Consistent Learning FrameworkModel Type=Image Model, Backbone=ACSNet [29]2026.06 | 81.6 | — | 71.9 | 75.8 | 73.7 | 74.1 | 0.878 | — | — | — | |
| ARTEMISLabeled Training Data Ratio=1/82026.06 | 80.8 | — | 69.4 | — | 70.9 | — | 83.9 | 63.1 | 4.6 | — | |
| DALAModel Type=Video Model2026.06 | 80.8 | — | 67.6 | 73.5 | 73.3 | 66.9 | 0.84 | — | — | — | |
| SSTANModel Type=Video Model2026.06 | 80.1 | — | 68.2 | 73.4 | 71.8 | 67.6 | 0.733 | — | — | — | |
| PNS+Supervision Setting=Fully Supervised2026.06 | 79.8 | — | 65.4 | — | 66.1 | — | — | 57.1 | 5 | 79.3 | |
| PNS+Category=VIDEO, Publish=OURS22, Code=Link2022.03 | 79.7 | 0.793 | 65.3 | 70.9 | 73.7 | 62.3 | — | — | — | — | |
| PNS+Mode=Unseen2024.06 | 79.7 | — | 65.3 | 70.9 | 73.7 | 62.3 | 79.3 | — | — | — | |
| PNS+2024.09 | 79.7 | — | — | 70.9 | 73.7 | 62.3 | 0.793 | — | — | — | |
| ARTEMISSupervision Setting=Scribble Supervision2026.06 | 79.6 | — | 67.5 | — | 68.7 | — | — | 60.9 | 4.8 | 81.6 | |
| CMLLabeled Training Data Ratio=1/82026.06 | 79.3 | — | 53.5 | — | 67.6 | — | 81.2 | 57.9 | 7.4 | — | |
| ACSNetModel Type=Image Model2026.06 | 79.3 | — | 63.6 | 68.4 | 70.8 | 61.8 | 0.787 | — | — | — | |
| ARTEMISLabeled Training Data Ratio=1/162026.06 | 79.2 | — | 67.1 | — | 68.2 | — | 81.4 | 60.2 | 5 | — | |
| ColonSegNetModel Type=Image Model2026.06 | 78.9 | — | 63.6 | 66.2 | 68.5 | 59.9 | 0.77 | — | — | — | |
| SEELabeled Training Data Ratio=1/82026.06 | 78.7 | — | 65.8 | — | 67.2 | — | 81 | 59.3 | 5.5 | — | |
| PraNetSupervision Setting=Fully Supervised2026.06 | 78.7 | — | 66.7 | — | 67.5 | — | — | 58.7 | 5.3 | 80.2 | |
| 2/3DCategory=VIDEO, Publish=MICCAI20, Code=R/T2022.03 | 78.6 | 0.775 | 63.4 | 68.8 | 70.6 | 60.7 | — | — | — | — | |
| 2/3DMode=Unseen2024.06 | 78.6 | — | 63.4 | 68.8 | 70.6 | 60.7 | 77.5 | — | — | — | |
| 2/3D2024.09 | 78.6 | — | — | 68.8 | 70.6 | 60.7 | 0.775 | — | — | — | |
| MATCategory=VIDEO, Publish=TIP20, Code=Link2022.03 | 78.5 | 0.755 | 57.8 | 64.5 | 71.2 | 57.9 | — | — | — | — | |
| ACSNetCategory=IMAGE, Publish=MICCAI20, Code=Link2022.03 | 78.3 | 0.787 | 63.6 | 68.4 | 70.8 | 61.8 | — | — | — | — | |
| SEESupervision Setting=Scribble Supervision2026.06 | 78 | — | 53 | — | 67 | — | — | 57 | 9.2 | 80.2 | |
| AD-MTLabeled Training Data Ratio=1/82026.06 | 77.6 | — | 51.7 | — | 66.2 | — | 80 | 56.5 | 9.1 | — | |
| SEELabeled Training Data Ratio=1/162026.06 | 77.5 | — | 55.5 | — | 63.1 | — | 78.3 | 53.9 | 6.7 | — | |
| ST-SAMLabeled Training Data Ratio=1/82026.06 | 77.4 | — | 54.1 | — | 64 | — | 79 | 55.5 | 7.2 | — | |
| MSRF-NetModel Type=Image Model2026.06 | 77.4 | — | 63.7 | 65.8 | 70.1 | 60.5 | 0.762 | — | — | — | |
| KnowSAMLabeled Training Data Ratio=1/162026.06 | 77.2 | — | 51.6 | — | 65.8 | — | 80.3 | 56.8 | 7.5 | — | |
| ARTEMISSupervision Setting=Point Supervision2026.06 | 77 | — | 52.7 | — | 64.4 | — | — | 55.5 | 8 | 78.6 | |
| PNSNetCategory=VIDEO, Publish=MICCAI21, Code=Link2022.03 | 76.7 | 0.755 | 60.9 | 65.6 | 67.5 | 57.9 | — | — | — | — | |
| PNS-NetMode=Unseen2024.06 | 76.7 | — | 60.9 | 65.6 | 67.5 | 57.9 | 75.5 | — | — | — | |
| PNS-Net2024.09 | 76.7 | — | — | 65.6 | 67.5 | 57.9 | 0.755 | — | — | — | |
| PNSSupervision Setting=Fully Supervised2026.06 | 76.7 | — | 60.9 | — | 61.5 | — | — | 53.9 | 5 | 75.5 | |
| TransNetRModel Type=Image Model2026.06 | 76.6 | — | 62.9 | 67.3 | 62.8 | 59.1 | 0.772 | — | — | — | |
| WS-SAMSupervision Setting=Scribble Supervision2026.06 | 76.3 | — | 49.5 | — | 65.7 | — | — | 56.3 | 9.1 | 79.7 | |
| CauSSLLabeled Training Data Ratio=1/82026.06 | 76.2 | — | 47.9 | — | 64.9 | — | 78.3 | 55.6 | 10.6 | — | |
| ST-SAMLabeled Training Data Ratio=1/162026.06 | 76.2 | — | 49.3 | — | 64.6 | — | 78.9 | 55.5 | 8.7 | — | |
| AD-MTLabeled Training Data Ratio=1/162026.06 | 75.8 | — | 49 | — | 65.7 | — | 79.3 | 56.3 | 9.9 | — | |
| MCFLabeled Training Data Ratio=1/82026.06 | 75.6 | — | 48.1 | — | 66.5 | — | 79 | 56.6 | 11.4 | — | |
| ProMaCSupervision Setting=Scribble Supervision2026.06 | 75.2 | — | 50.8 | — | 65 | — | — | 56.1 | 11.3 | 78.5 | |
| ProMaCSupervision Setting=Point Supervision2026.06 | 75.2 | — | 49.3 | — | 63.8 | — | — | 54.1 | 11 | 77.6 | |
| KnowSAMLabeled Training Data Ratio=1/82026.06 | 74.9 | — | 59.6 | — | 60.2 | — | 74.5 | 52.3 | 5.7 | — | |
| CMLLabeled Training Data Ratio=1/162026.06 | 74.7 | — | 47.3 | — | 64.1 | — | 78.2 | 54.9 | 10 | — | |
| CauSSLLabeled Training Data Ratio=1/162026.06 | 74.5 | — | 45.5 | — | 65.1 | — | 78.7 | 55.6 | 10.6 | — | |
| WeakPolypSupervision Setting=Scribble Supervision2026.06 | 74.5 | — | 45.2 | — | 64.3 | — | — | 54.4 | 11 | 78.2 | |
| SEESupervision Setting=Point Supervision2026.06 | 74.2 | — | 46.1 | — | 63.1 | — | — | 53.6 | 11.2 | 77 | |
| WS-SAMSupervision Setting=Point Supervision2026.06 | 73.7 | — | 43.9 | — | 63.9 | — | — | 54.5 | 11.6 | 77.3 | |
| SCODSupervision Setting=Scribble Supervision2026.06 | 73.4 | — | 42.8 | — | 62.9 | — | — | 52.9 | 11.3 | 77 | |
| FSNetCategory=VIDEO, Publish=ICCV21, Code=Link2022.03 | 72.4 | 0.694 | 54.1 | 61.1 | 69.9 | 49.1 | — | — | — | — | |
| SCWSSupervision Setting=Scribble Supervision2026.06 | 72.2 | — | 41.9 | — | 60.4 | — | — | 50.2 | 12.7 | 74.7 | |
| FLA-NetMode=Unseen2024.06 | 72.1 | — | 54 | 59.2 | 62.8 | 52.2 | 70.1 | — | — | — | |
| FLA-Net2024.09 | 72.1 | — | — | 59.2 | 62.8 | 52.2 | 0.701 | — | — | — | |
| FLA-NetModel Type=Video Model2026.06 | 72.1 | — | 54 | 59.2 | 62.8 | 52.2 | 0.701 | — | — | — | |
| PraNetCategory=IMAGE, Publish=MICCAI20, Code=Link2022.03 | 71.7 | 0.735 | 54.4 | 60.7 | 59.8 | 51.2 | — | — | — | — | |
| PraNetModel Type=Image Model2026.06 | 71.7 | — | 54.4 | 60.7 | 59.8 | 51.2 | 0.735 | — | — | — | |
| TELSupervision Setting=Point Supervision2026.06 | 71.5 | — | 39.8 | — | 61.7 | — | — | 51.8 | 13.3 | 75.1 | |
| GenSAMSupervision Setting=Point Supervision2026.06 | 71.4 | — | 39.7 | — | 62.4 | — | — | 51.9 | 13.1 | 76 | |
| GenSAMSupervision Setting=Scribble Supervision2026.06 | 71.3 | — | 39.4 | — | 61.3 | — | — | 51 | 13.3 | 75 | |
| TELSupervision Setting=Scribble Supervision2026.06 | 71.2 | — | 42 | — | 59.5 | — | — | 50.3 | 14 | 73.5 | |
| MTLabeled Training Data Ratio=1/82026.06 | 70.7 | — | 40 | — | 63.7 | — | 74.8 | 53.5 | 16 | — | |
| SANetCategory=IMAGE, Publish=MICCAI21, Code=Link2022.03 | 70.6 | 0.743 | 52.6 | 58 | 59.8 | 50.5 | — | — | — | — | |
| MCFLabeled Training Data Ratio=1/162026.06 | 70.5 | — | 40.4 | — | 61.6 | — | 74.4 | 51.9 | 14.8 | — | |
| SCODSupervision Setting=Point Supervision2026.06 | 70.1 | — | 37.9 | — | 60.2 | — | — | 50.3 | 14.6 | 73.8 | |
| MedNeXtModel Type=Image Model2026.06 | 69.9 | — | 52.2 | 57.5 | 61.1 | 50.8 | 0.701 | — | — | — | |
| SCWSSupervision Setting=Point Supervision2026.06 | 68.6 | — | 35.2 | — | 57.7 | — | — | 47.3 | 14.9 | 71.6 | |
| UNet++Category=IMAGE, Publish=TMI18, Code=Link2022.03 | 68.5 | 0.697 | 48 | 54.4 | 55.4 | 46.7 | — | — | — | — | |
| MTLabeled Training Data Ratio=1/162026.06 | 68.5 | — | 34.8 | — | 57.9 | — | 71.7 | 47.4 | 15.3 | — | |
| U-Net++Model Type=Image Model2026.06 | 68.5 | — | 48 | 54.4 | 55.4 | 46.7 | 0.697 | — | — | — | |
| PCSACategory=VIDEO, Publish=AAAI20, Code=Link2022.03 | 68.2 | 0.66 | 44.2 | 51 | 58.4 | 41.5 | — | — | — | — | |
| UNetCategory=IMAGE, Publish=MICCAI15, Code=Link2022.03 | 67 | 0.679 | 45.7 | 52.7 | 54.2 | 42.9 | — | — | — | — | |
| COSNetCategory=VIDEO, Publish=TPAMI19, Code=Link2022.03 | 67 | 0.627 | 44.3 | 50.6 | 60.6 | 38 | — | — | — | — | |
| U-NetModel Type=Image Model2026.06 | 67 | — | 45.7 | 52.7 | 54.2 | 42.9 | 0.679 | — | — | — | |
| SAM-WSSupervision Setting=Point Supervision2026.06 | 64.8 | — | 29.8 | — | 56.1 | — | — | 45.6 | 19.4 | 68.6 | |
| SAM-SLabeled Training Data Ratio=1/82026.06 | 61.7 | — | 24.4 | — | 46.9 | — | 60.2 | 36.3 | 22 | — | |
| SAM-SLabeled Training Data Ratio=1/162026.06 | 58.5 | — | 21.4 | — | 41.8 | — | 58 | 31.6 | 22.9 | — | |
| SAM-WSSupervision Setting=Scribble Supervision2026.06 | 56.9 | — | 20.2 | — | 35.2 | — | — | 25.8 | 25.1 | 52.3 | |
| DCFCategory=VIDEO, Publish=ICCV21, Code=Link2022.03 | 51.4 | 0.522 | 26.3 | 30.3 | 31.7 | 36.4 | — | — | — | — | |
| AMDCategory=VIDEO, Publish=NeurIPS21, Code=Link2022.03 | 47.2 | 0.527 | 12.8 | 14.1 | 25.2 | 21.3 | — | — | — | — |