Methods › Computer Vision › Image Models › CvT

Convolutional Vision Transformer

CvT

12 papers tagged archive 2025-07-28

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.

PaperSource

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.

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.

TaskPapers
Image Classification3
Semantic Segmentation2
Transfer Learning2
image-classification2
Continual Learning1
Contrastive Learning1
Deep Learning1
Denoising1
GPU1
Image Denoising1
Image Reconstruction1
Inductive Bias1
Instance Segmentation1
Mamba1
Prediction1
State Space Models1
Time Series1
Time Series Analysis1

Usage over time archive 2025-07-28

Papers per year tagged with CvT: 2021 to 2025, peak 4 4 0 2021: 3 papers 2021 2022: 4 papers 2022 2023: 1 paper 2023 2024: 3 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (12 dated). Bars are counts, not a trend claim.

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

Image ModelsVision Transformers

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