</> Code with Papers by Syntology

Methods › Computer Vision › Convolutions › Grouped Convolution

Grouped Convolution

575 papers tagged archive 2025-07-28

Introduced by Alex Krizhevsky et al. in ImageNet Classification with Deep Convolutional Neural Networks

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

A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a network learn a varied set of low level and high level features. The original motivation of using Grouped Convolutions in AlexNet was to distribute the model over multiple GPUs as an engineering compromise. But later, with models such as ResNeXt, it was shown this module could be used to improve classification accuracy. Specifically by exposing a new dimension through grouped convolutions, cardinality (the size of set of transformations), we can increase accuracy by increasing it.

PaperSourceSee Code · prlz77/ResNeXt.pytorch

Papers archive 2025-07-28

30 shown of 575, 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 368 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 Classification85
General Classification77
Object Detection72
image-classification60
object-detection56
Quantization43
Semantic Segmentation42
Classification38
GPU36
Object35
Transfer Learning35
Segmentation29
Deep Learning24
Object Recognition24
Instance Segmentation17
Model Compression17
Neural Architecture Search17
CPU16
Data Augmentation15
Representation Learning12

Usage over time archive 2025-07-28

Papers per year tagged with Grouped Convolution: 2012 to 2025, peak 136 136 0 2012: 1 paper 2012 2013: 0 papers 2013 2014: 3 papers 2014 2015: 15 papers 2015 2016: 31 papers 2016 2017: 57 papers 2017 2018: 110 papers 2018 2019: 136 papers 2019 2020: 82 papers 2020 2021: 55 papers 2021 2022: 27 papers 2022 2023: 21 papers 2023 2024: 24 papers 2024 2025: 13 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (575 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