Cirrhosis Classification on D_histo^2 N=49
0.95AUCBYOL
Evaluation results
| Method | Links | |
|---|---|---|
| BYOLBackbone=TinyNet, Weak labels=false, Depth pos.=false2023.07 | 0.95 | |
| SupConBackbone=TinyNet, Weak labels=true, Depth pos.=false2023.07 | 0.93 | |
| Weakly-supervised positional contrastive learningBackbone=TinyNet, Weak labels=true, Depth pos.=true2023.07 | 0.91 | |
| SimCLRBackbone=TinyNet, Weak labels=false, Depth pos.=false2023.07 | 0.88 | |
| Weakly-supervised positional contrastive learningBackbone=ResNet-18, Weak labels=true, Depth pos.=true2023.07 | 0.85 | |
| SimCLRBackbone=ResNet-18, Weak labels=false, Depth pos.=false2023.07 | 0.82 | |
| depth-AwareBackbone=ResNet-18, Weak labels=false, Depth pos.=true2023.07 | 0.82 | |
| depth-AwareBackbone=TinyNet, Weak labels=false, Depth pos.=true2023.07 | 0.81 | |
| BYOLBackbone=ResNet-18, Weak labels=false, Depth pos.=false2023.07 | 0.77 | |
| ImageNet (frozen representations)Backbone=ResNet-18, Weak labels=false, Depth pos.=false2023.07 | 0.76 | |
| None (random initialization)Backbone=TinyNet, Weak labels=false, Depth pos.=false2023.07 | 0.75 | |
| None (random initialization)Backbone=ResNet-18, Weak labels=false, Depth pos.=false2023.07 | 0.73 | |
| SupConBackbone=ResNet-18, Weak labels=true, Depth pos.=false2023.07 | 0.69 | |
| SupervisedBackbone=TinyNet, Weak labels=false, Depth pos.=false2023.07 | 0.65 | |
| SupervisedBackbone=ResNet-18, Weak labels=false, Depth pos.=false2023.07 | 0.56 |