Methods › Computer Vision › Image Models › CvT
Convolutional Vision Transformer
CvT
Introduced by Haiping Wu et al. in CvT: Introducing Convolutions to Vision Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Convolutional vision Transformer (CvT) is an architecture which incorporates convolutions into the Transformer. The CvT design introduces convolutions to two core sections of the ViT architecture.
First, the Transformers are partitioned into multiple stages that form a hierarchical structure of Transformers. The beginning of each stage consists of a convolutional token embedding that performs an overlapping convolution operation with stride on a 2D-reshaped token map (i.e., reshaping flattened token sequences back to the spatial grid), followed by layer normalization. This allows the model to not only capture local information, but also progressively decrease the sequence length while simultaneously increasing the dimension of token features across stages, achieving spatial downsampling while concurrently increasing the number of feature maps, as is performed in CNNs.
Second, the linear projection prior to every self-attention block in the Transformer module is replaced with a proposed convolutional projection, which employs a s × s depth-wise separable convolution operation on an 2D-reshaped token map. This allows the model to further capture local spatial context and reduce semantic ambiguity in the attention mechanism. It also permits management of computational complexity, as the stride of convolution can be used to subsample the key and value matrices to improve efficiency by 4× or more, with minimal degradation of performance.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 16 in the graph, strongest link: official). This answer is about arXiv:2103.15808, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2103.15808 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 39 ran (of which 19 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified (of 47 harvested samples) · 8 pointer-only (licence). 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: 12 · with a code link: 4 · where Syntology ran a sample: 3 (3 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 (3 of 12 tagged: 3 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 12 of 12, 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.
-
Residual Transformer Fusion Network for Salt and Pepper Image Denoising 13 Feb 2025 · 0 repositories · arXiv:2502.09000
-
Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis 26 Mar 2024 · 2 repositories · arXiv:2403.18063Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
A Comparison of Deep Learning Models for Proton Background Rejection with the AMS Electromagnetic Calorimeter 26 Feb 2024 · 0 repositories · arXiv:2402.16285
-
On Convolutional Vision Transformers for Yield Prediction 8 Feb 2024 · 0 repositories · arXiv:2402.05557
-
Making Vision Transformers Truly Shift-Equivariant 25 May 2023 · 0 repositories · arXiv:2305.16316
-
A Novel Framework for Decentralized Dynamic Resource Allocation Using Voronoi Tessellations 30 Nov 2022 · 0 repositories · arXiv:2212.00140
-
Online Continual Learning with Contrastive Vision Transformer 24 Jul 2022 · 0 repositories · arXiv:2207.13516
-
SimA: Simple Softmax-free Attention for Vision Transformers 17 Jun 2022 · 1 repository · arXiv:2206.08898Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Convolutional Xformers for Vision 25 Jan 2022 · 1 repository · arXiv:2201.10271
-
Energy-optimal Design and Control of Electric Powertrains under Motor Thermal Constraints 15 Nov 2021 · 0 repositories · arXiv:2111.07711
-
Convolutional Gated MLP: Combining Convolutions & gMLP 6 Nov 2021 · 0 repositories · arXiv:2111.03940
-
CvT: Introducing Convolutions to Vision Transformers 29 Mar 2021 · 16 repositories · arXiv:2103.15808Syntology official (archive's flag): 10 ran · 39 ran (of which 19 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified (of 47 harvested samples) · 8 pointer-only (licence)
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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