Methods › Computer Vision › Convolutions › Large Kernel Size

Large convolutional kernels

Large Kernel Size

6 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.

Usage of larger than typical convolutional kernel sizes, as also seen in 'Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs'

Paper Source

Papers archive 2025-07-28

6 shown of 6, 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.

3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
29 Sep 2022 · 2 repositories · arXiv:2209.15076

Syntology ran 5 of 7 samples · 2 unverified · 4 pointer-only (licence)
Deep Multi-Scale Representation Learning with Attention for Automatic Modulation Classification
31 Aug 2022 · 0 repositories · arXiv:2209.03764
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
13 Mar 2022 · 8 repositories · arXiv:2203.06717

Syntology ran 2 of 8 samples · 6 unverified
A ConvNet for the 2020s
10 Jan 2022 · 54 repositories · arXiv:2201.03545

Syntology ran 54 of 80 samples · 26 unverified · 11 pointer-only (licence)
Understanding Kernel Size in Blind Deconvolution
6 Jun 2017 · 1 repository · arXiv:1706.01797
ImageNet Classification with Deep Convolutional Neural Networks
1 Dec 2012 · 23 repositories

Tasks archive 2025-07-28

18 tasks 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	3
Classification	2
Semantic Segmentation	2
Deblurring	1
Domain Generalization	1
Ensemble Learning	1
GPU	1
General Classification	1
Graph Classification	1
Image Segmentation	1
Medical Image Segmentation	1
Object Detection	1
Object Recognition	1
Real-Time Object Detection	1
Representation Learning	1
Segmentation	1
Transfer Learning	1
image-classification	1

Usage over time archive 2025-07-28

Papers per year the archive tags with this method, by the paper's archive date (6 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