Methods › General › Attention Modules › GPSA
Gated Positional Self-Attention
GPSA
Introduced by Stéphane d'Ascoli et al. in ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Gated Positional Self-Attention (GPSA) is a self-attention module for vision transformers, used in the ConViT architecture, that can be initialized as a convolutional layer -- helping a ViT learn inductive biases about locality.
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.
-
What do Vision Transformers Learn? A Visual Exploration 13 Dec 2022 · 1 repository · arXiv:2212.06727
-
Conviformers: Convolutionally guided Vision Transformer 17 Aug 2022 · 1 repository · arXiv:2208.08900
-
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases 19 Mar 2021 · 9 repositories · arXiv:2103.10697
Tasks archive 2025-07-28
5 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 |
|---|---|
| Image Classification | 2 |
| image-classification | 2 |
| Fine-Grained Image Classification | 1 |
| Inductive Bias | 1 |
| Language Modelling | 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