The Lovasz-Softmax loss is a loss function for multiclass semantic segmentation that incorporates the softmax operation in the Lovasz extension. The Lovasz extension is a means by which we can achieve direct optimization of the mean intersection-over-union loss in neural networks.
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 4 | 26.67% |
Image Segmentation | 2 | 13.33% |
3D Semantic Segmentation | 2 | 13.33% |
Autonomous Driving | 2 | 13.33% |
Decoder | 2 | 13.33% |
Medical Image Segmentation | 1 | 6.67% |
Scene Understanding | 1 | 6.67% |
Robust 3D Semantic Segmentation | 1 | 6.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |