Abnormal classification on In-house (test)
88.4AUCDisAsymNet
Evaluation results
| Method | Links | |
|---|---|---|
| DisAsymNetBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 88.4 | |
| AsyC & AsyDBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 88.1 | |
| Wang et al.Backbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 86.5 | |
| AsyCBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 86 | |
| AsyD & SynBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 84.6 | |
| AsyDBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 83.2 | |
| ResNet-18Backbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 82.8 | |
| HAMBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 82.8 | |
| Late fusionBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 82.5 | |
| CVTBackbone=ResNet-18, Pre-training=ImageNet, Image Size=1024x5122023.07 | 82.1 |