Methods › Computer Vision › Convolutions › Dilated Convolution

Dilated Convolution

679 papers tagged archive 2025-07-28

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

Dilated Convolutions are a type of convolution that “inflate” the kernel by inserting holes between the kernel elements. An additional parameter l (dilation rate) indicates how much the kernel is widened. There are usually l-1 spaces inserted between kernel elements.

Note that concept has existed in past literature under different names, for instance the algorithme a trous, an algorithm for wavelet decomposition (Holschneider et al., 1987; Shensa, 1992).

Source: Multi-Scale Context Aggregation by Dilated ConvolutionsSee Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 679, 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 438 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
Semantic Segmentation215
Segmentation151
Reinforcement Learning (RL)85
reinforcement-learning66
Object Detection61
Deep Reinforcement Learning58
Image Segmentation58
object-detection53
Reinforcement Learning51
Decoder46
Object34
Image Classification29
Autonomous Driving28
Continuous Control28
continuous-control28
image-classification26
Instance Segmentation24
General Classification22
MuJoCo20
Data Augmentation17

Usage over time archive 2025-07-28

Papers per year tagged with Dilated Convolution: 2015 to 2025, peak 120 120 0 2015: 1 paper 2015 2016: 6 papers 2016 2017: 19 papers 2017 2018: 49 papers 2018 2019: 59 papers 2019 2020: 115 papers 2020 2021: 120 papers 2021 2022: 100 papers 2022 2023: 71 papers 2023 2024: 106 papers 2024 2025: 33 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (679 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