Methods › Computer Vision › Generative Adversarial Networks › BigGAN-deep
BigGAN-deep
Introduced by Andrew Brock et al. in Large Scale GAN Training for High Fidelity Natural Image Synthesis
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
BigGAN-deep is a deeper version (4x) of BigGAN. The main difference is a slightly differently designed residual block. Here the z vector is concatenated with the conditional vector without splitting it into chunks. It is also based on residual blocks with bottlenecks. BigGAN-deep uses a different strategy than BigGAN aimed at preserving identity throughout the skip connections. In G, where the number of channels needs to be reduced, BigGAN-deep simply retains the first group of channels and drop the rest to produce the required number of channels. In D, where the number of channels should be increased, BigGAN-deep passes the input channels unperturbed, and concatenates them with the remaining channels produced by a 1 × 1 convolution. As far as the network configuration is concerned, the discriminator is an exact reflection of the generator.
There are two blocks at each resolution (BigGAN uses one), and as a result BigGAN-deep is four times deeper than BigGAN. Despite their increased depth, the BigGAN-deep models have significantly fewer parameters mainly due to the bottleneck structure of their residual blocks.
Papers archive 2025-07-28
11 shown of 11, 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.
-
Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning 7 Mar 2023 · 1 repository · arXiv:2303.08046
-
Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN 16 Nov 2022 · 0 repositories · arXiv:2211.08742
-
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values 3 Mar 2022 · 1 repository · arXiv:2203.01993
-
Sinogram Denoise Based on Generative Adversarial Networks 9 Aug 2021 · 0 repositories · arXiv:2108.03903
-
Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior 18 Jun 2021 · 0 repositories · arXiv:2106.10359
-
Cascaded Diffusion Models for High Fidelity Image Generation 30 May 2021 · 0 repositories · arXiv:2106.15282
-
A Geometric Analysis of Deep Generative Image Models and Its Applications 1 Jan 2021 · 1 repository
-
LOGAN: Local Group Bias Detection by Clustering 6 Oct 2020 · 1 repository · arXiv:2010.02867
-
Allpass Feedback Delay Networks 14 Jul 2020 · 0 repositories · arXiv:2007.07337
-
LOGAN: Latent Optimisation for Generative Adversarial Networks 2 Dec 2019 · 1 repository · arXiv:1912.00953Syntology ran 2 of 8 samples · 6 unverified
-
Large Scale GAN Training for High Fidelity Natural Image Synthesis 28 Sep 2018 · 35 repositories · arXiv:1809.11096Syntology ran 14 of 41 samples · 27 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
19 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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