Lesion Segmentation On University Of Waterloo
Metriken
Dice score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Dice score | Paper Title | Repository |
|---|---|---|---|
| DeepLabV3+ | 0.883 ±0.108 | Skin Lesion Segmentation Using Atrous Convolution via DeepLab v3 | - |
| U-Net | 0.836 ±0.132 | U-Net: Convolutional Networks for Biomedical Image Segmentation | |
| DTP-Net | 0.884 ±0.100 | DTP-Net: A convolutional neural network model to predict threshold for localizing the lesions on dermatological macro-images | |
| FCN-8s | 0.870 ±0.063 | Fully Connected Deep Structured Networks | - |
| SegNet | 0.854 ±0.088 | SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation |
0 of 5 row(s) selected.