Methods › Computer Vision › Generative Models › DCGAN

Deep Convolutional GAN

DCGAN

82 papers tagged archive 2025-07-28

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

DCGAN, or Deep Convolutional GAN, is a generative adversarial network architecture. It uses a couple of guidelines, in particular:

Source: Unsupervised Representation Learning with Deep...See Code · eriklindernoren/PyTorch-GAN

Papers archive 2025-07-28

30 shown of 82, 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 74 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 Generation24
Generative Adversarial Network16
Data Augmentation8
Diversity6
Translation5
Conditional Image Generation3
Deep Learning3
Image Classification3
Anomaly Detection2
BIG-bench Machine Learning2
Decoder2
GPU2
General Classification2
Image-to-Image Translation2
Medical Image Generation2
Object Detection2
Pedestrian Detection2
Privacy Preserving2
Representation Learning2
Style Transfer2

Usage over time archive 2025-07-28

Papers per year tagged with DCGAN: 2015 to 2025, peak 15 15 0 2015: 1 paper 2015 2016: 1 paper 2016 2017: 9 papers 2017 2018: 10 papers 2018 2019: 9 papers 2019 2020: 15 papers 2020 2021: 15 papers 2021 2022: 8 papers 2022 2023: 6 papers 2023 2024: 7 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (82 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

Generative Models

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