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.
In Syntology about another paper, arXiv:2410.19313: repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The lookup matched 'COAT' ignoring case. About another paper: this answer is about arXiv:2410.19313, while the archive credits arXiv:2104.06399.
From the lookup's note on this name: The same name also belongs to “Co-scale conv-attentional image Transformers (CoaT)”, a method in the paper “Co-Scale Conv-Attentional Image Transformers” (arXiv:2104.06399, 475 citations), which the lookup finds cited far more than the paper this answer is about (39 citations), so this answer may be about a different sense of the name. For arXiv:2104.06399: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2410.19313 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 5 · with a code link: 2 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 5 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 5 of 5, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
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 official (archive's flag): 7 ran · 17 ran (of which 11 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 22 harvested samples) · 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