Methods › Computer Vision › Pooling Operations › SoftPool
Soft Pooling
SoftPool
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SoftPool: a fast and efficient method that sums exponentially weighted activations. Compared to a range of other pooling methods, SoftPool retains more information in the downsampled activation maps. More refined downsampling leads to better classification accuracy.
Papers archive 2025-07-28
3 shown of 3, 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.
-
FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality 15 Jan 2024 · 0 repositories · arXiv:2401.07558
-
Dual Stream Computer-Generated Image Detection Network Based On Channel Joint And Softpool 7 Jul 2022 · 1 repository · arXiv:2207.03205
-
Refining activation downsampling with SoftPool 2 Jan 2021 · 8 repositories · arXiv:2101.00440
Tasks archive 2025-07-28
3 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 |
|---|---|
| Action Recognition | 1 |
| Federated Learning | 1 |
| Image Forensics | 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