Methods › Computer Vision › Convolutions › Depthwise Separable Convolution

Depthwise Separable Convolution

1,174 papers tagged archive 2025-07-28

Introduced by Francois Chollet in Xception: Deep Learning With Depthwise Separable Convolutions

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

While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution splits the computation into two steps: depthwise convolution applies a single convolutional filter per each input channel and pointwise convolution is used to create a linear combination of the output of the depthwise convolution. The comparison of standard convolution and depthwise separable convolution is shown to the right.

Credit: Depthwise Convolution Is All You Need for Learning Multiple Visual Domains

PaperSourceSee Code · kwotsin/TensorFlow-Xception

Papers archive 2025-07-28

30 shown of 1,174, 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 514 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 Classification207
Transfer Learning174
image-classification154
Object Detection136
object-detection117
Classification86
Neural Architecture Search83
Semantic Segmentation80
Deep Learning68
Quantization66
Data Augmentation58
General Classification58
Diagnostic53
GPU49
Segmentation47
Object31
Decoder29
Computational Efficiency27
Model Compression27
Instance Segmentation26

Usage over time archive 2025-07-28

Papers per year tagged with Depthwise Separable Convolution: 2016 to 2025, peak 212 212 0 2016: 1 paper 2016 2017: 7 papers 2017 2018: 30 papers 2018 2019: 103 papers 2019 2020: 181 papers 2020 2021: 212 papers 2021 2022: 184 papers 2022 2023: 192 papers 2023 2024: 191 papers 2024 2025: 73 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (1,174 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