Methods › General › Activation Functions › Gumbel Activation
Gumbel Cross Entropy
Gumbel Activation
Introduced by Konstantinos Panagiotis Alexandridis et al. in Long-tailed Instance Segmentation using Gumbel Optimized Loss
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Gumbel activation function, is defined using the cumulative Gumbel distribution and it can be used to perform Gumbel regression. Gumbel activation is an alternative activation function to the sigmoid or softmax activation functions and can be used to transform the unormalised output of a model to probability. Gumbel activation η_(Gumbel) is defined as follows:
η_(Gumbel)(qᵢ) = exp(-exp(-qᵢ))
It can be combined with Cross Entropy loss function to solve long-tailed classification problems. Gumbel Cross Entropy (GCE) is defined as follows:
GCE(η_(Gumbel)(qᵢ),yᵢ) = -yᵢ log(η_(Gumbel)(qᵢ))+ (1-yᵢ) log(1-η_(Gumbel)(qᵢ))
Papers archive 2025-07-28
1 shown of 1, 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.
-
Long-tailed Instance Segmentation using Gumbel Optimized Loss 22 Jul 2022 · 1 repository · arXiv:2207.10936
Tasks archive 2025-07-28
4 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 |
|---|---|
| Instance Segmentation | 1 |
| Object Detection | 1 |
| Segmentation | 1 |
| object-detection | 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