Methods › Computer Vision › Convolutions › Depthwise Convolution

Depthwise Convolution

introduced 2016 1,321 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D convolution performed over multiple input channels, the filter is as deep as the input and lets us freely mix channels to generate each element in the output. In contrast, depthwise convolutions keep each channel separate. To summarize the steps, we:

  1. Split the input and filter into channels.
  2. We convolve each input with the respective filter.
  3. We stack the convolved outputs together.

Image Credit: Chi-Feng Wang

Papers archive 2025-07-28

30 shown of 1,321, 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.

Tasks archive 2025-07-28

20 shown of 568 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 Classification232
Transfer Learning175
image-classification169
Object Detection151
object-detection129
Semantic Segmentation105
Neural Architecture Search92
Classification90
Deep Learning75
Quantization68
General Classification66
GPU60
Data Augmentation59
Segmentation59
Diagnostic57
Decoder34
Object34
Computational Efficiency33
Instance Segmentation30
Model Compression29

Usage over time archive 2025-07-28

Papers per year tagged with Depthwise Convolution: 2016 to 2025, peak 244 244 0 2016: 1 paper 2016 2017: 9 papers 2017 2018: 37 papers 2018 2019: 118 papers 2019 2020: 199 papers 2020 2021: 244 papers 2021 2022: 210 papers 2022 2023: 213 papers 2023 2024: 209 papers 2024 2025: 81 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (1,321 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

Convolutions

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