Methods › Computer Vision › Convolutions › DimConv
Dimension-wise Convolution
DimConv
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Dimension-wise Convolution, or DimConv, is a type of convolution that can encode depth-wise, width-wise, and height-wise information independently. To achieve this, DimConv extends depthwise convolutions to all dimensions of the input tensor X ∈ℝ^(D×H×W), where W, H, and D corresponds to width, height, and depth of X. DimConv has three branches, one branch per dimension. These branches apply D depth-wise convolutional kernels k_D ∈ℝ^(1×n×n) along depth, W width-wise convolutional kernels k_W ∈ℝ^(n×1×1) along width, and H height-wise convolutional kernels k_H ∈ℝ^(n×1×n) kernels along height to produce outputs Y_D, Y_W, and Y_H ∈ℝ^(D×H×W) that encode information from all dimensions of the input tensor. The outputs of these independent branches are concatenated along the depth dimension, such that the first spatial plane of Y_D, Y_W, and Y_H are put together and so on, to produce the output Y_(Dim) ={Y_D, Y_W, Y_H} ∈ℝ^(3D×H×W).
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.
-
DiCENet: Dimension-wise Convolutions for Efficient Networks 8 Jun 2019 · 2 repositories · arXiv:1906.03516Syntology ran 0 of 1 samples · 1 unverified
Tasks archive 2025-07-28
8 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