Methods › Computer Vision › Vision Transformers › CoaT
Co-Scale Conv-attentional Image Transformer
CoaT
Introduced by Weijian Xu et al. in Co-Scale Conv-Attentional Image Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Co-Scale Conv-Attentional Image Transformer (CoaT) is a Transformer-based image classifier equipped with co-scale and conv-attentional mechanisms. First, the co-scale mechanism maintains the integrity of Transformers' encoder branches at individual scales, while allowing representations learned at different scales to effectively communicate with each other. Second, the conv-attentional mechanism is designed by realizing a relative position embedding formulation in the factorized attention module with an efficient convolution-like implementation. CoaT empowers image Transformers with enriched multi-scale and contextual modeling capabilities.
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.
-
Enhance Mobile Agents Thinking Process Via Iterative Preference Learning 18 May 2025 · 0 repositories · arXiv:2505.12299
-
What do Vision Transformers Learn? A Visual Exploration 13 Dec 2022 · 1 repository · arXiv:2212.06727
-
Exploring Advances in Transformers and CNN for Skin Lesion Diagnosis on Small Datasets 30 May 2022 · 0 repositories · arXiv:2205.15442
-
Exploring and Improving Mobile Level Vision Transformers 30 Aug 2021 · 0 repositories · arXiv:2108.13015
-
Co-Scale Conv-Attentional Image Transformers 13 Apr 2021 · 9 repositories · arXiv:2104.06399Syntology ran 17 of 22 samples · 5 unverified · 6 pointer-only (licence)
Tasks archive 2025-07-28
6 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 |
|---|---|
| Continual Pretraining | 1 |
| Instance Segmentation | 1 |
| Language Modelling | 1 |
| Object Detection | 1 |
| Semantic 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