Methods › Computer Vision › Vision Transformers › LocalViT
LocalViT
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
LocalViT aims to introduce depthwise convolutions to enhance local features modeling capability of ViTs. The network, as shown in Figure (c), brings localist mechanism into transformers through the depth-wise convolution (denoted by "DW"). To cope with the convolution operation, the conversation between sequence and image feature map is added by "Seq2Img" and "Img2Seq". The computation is as follows:
𝐘ʳ=f(f(𝐙ʳ ⊛𝐖₁ʳ ) ⊛𝐖_d ) ⊛𝐖₂ʳ
where 𝐖_d ∈ℝ^(γd ×1 ×k ×k) is the kernel of the depth-wise convolution.
The input (sequence of tokens) is first reshaped to a feature map rearranged on a 2D lattice. Two convolutions along with a depth-wise convolution are applied to the feature map. The feature map is reshaped to a sequence of tokens which are used as by the self-attention of the network transformer layer.
Papers archive 2025-07-28
1 shown of 1, 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.
-
LocalViT: Bringing Locality to Vision Transformers 12 Apr 2021 · 2 repositories · arXiv:2104.05707Syntology ran 3 of 6 samples · 3 unverified
Tasks archive 2025-07-28
1 task 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 | 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