Methods › General › Loss Functions › Lovasz-Softmax
Lovasz-Softmax
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation 22 Dec 2020 · 1 repository · arXiv:2012.11847
-
Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index 26 Oct 2020 · 0 repositories · arXiv:2010.13499
-
TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module 24 Aug 2020 · 0 repositories · arXiv:2008.10544
-
SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving 7 Mar 2020 · 5 repositories · arXiv:2003.03653Syntology ran 4 of 11 samples · 7 unverified · 1 pointer-only (licence)
-
The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks 1 Jun 2018 · 2 repositories
Tasks archive 2025-07-28
10 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Segmentation | 4 |
| Semantic Segmentation | 4 |
| 3D Semantic Segmentation | 2 |
| Autonomous Driving | 2 |
| Decoder | 2 |
| Image Segmentation | 2 |
| Generative Adversarial Network | 1 |
| Medical Image Segmentation | 1 |
| Robust 3D Semantic Segmentation | 1 |
| Scene Understanding | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections