Loss Functions
Dice Loss
Introduced by Sudre et al. in Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations\begin{equation} DiceLoss\left( y, \overline{p} \right) = 1 - \dfrac{\left( 2y\overline{p} + 1 \right)} {\left( y+\overline{p } + 1 \right)} \end{equation}
Source: Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationsPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 34 | 20.86% |
| Image Segmentation | 21 | 12.88% |
| Medical Image Segmentation | 13 | 7.98% |
| Tumor Segmentation | 11 | 6.75% |
| Brain Tumor Segmentation | 8 | 4.91% |
| Lesion Segmentation | 5 | 3.07% |
| Computed Tomography (CT) | 5 | 3.07% |
| Anatomy | 4 | 2.45% |
| Boundary Detection | 3 | 1.84% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
