Home › Code › DiffAugment

DiffAugment

Syntologyentry name in harvested coderead from the graph 2026-09-24

DiffAugment appears in the code Syntology harvested for 28 papers, as 31 distinct code bodies found in 36 places (a place is one code body under one paper). At least one of them ran in 10 of the papers; 6 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named DiffAugment do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 15 of the 31 distinct code bodies named DiffAugment; 16 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
9ran · fixture could not drive it
5ran
16unverified
6fingerprinted

Licence is a property of each copy, so it is counted per place: 11 of the 36 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

28 papers shown of 28, newest first; 36 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution added by Syntology 2026-09 (from id) SHH-Han/DNF-SR/dinov3_gan/dinov3_convnext_disc.py 1d566d068b0ed0af unverified licence not identified · pointer only
FedHPro: Federated Hyper-Prototype Learning via Gradient Matching added by Syntology 2026-05 (from id) mala-lab/FedHPro/main_run.py 655f5003e174acea ran · fixture could not drive it no licence file found · pointer only
A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence added by Syntology 2026-05 (from id) dnkameni/SwiGAN/modules/diff_augment.py e8c7431bf87b3d63 ran no licence file found · pointer only
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities 18 Oct 2024 haoosz/BiGR/bae/diffaug.py 1d566d068b0ed0af unverified MIT (permissive)
SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching 28 May 2024 Yongalls/SelMatch/distill.py ef316248cd525d06 unverified no licence file found · pointer only
DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations 23 Jan 2024 mlvlab/DDMI/losses/diffaugment.py 4206702962945b57 ran MIT (permissive)
Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution 30 Dec 2023 csslc/ccsr/models/DiffAugment.py d5662fd75b69cda4 ran Apache-2.0 (permissive)
DataDAM: Efficient Dataset Distillation with Attention Matching 29 Sep 2023 datadistillation/datadam/main_DataDAM.py 351e66f1c6171f1f unverified no licence file found · pointer only
Towards Mitigating Architecture Overfitting on Distilled Datasets 8 Sep 2023 cityu-mlo/mitigate_architecture_overfitting/utils.py 49fec08c0e9cb0d6 unverified no licence file found · pointer only
Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification 27 Jul 2023 xmed-lab/fed-mas/methods/utils.py c3bcb463338e8c6e ran no licence file found · pointer only
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models 7 Jun 2023 Zhendong-Wang/Diffusion-GAN/diffusion-projected-gan/pg_modules/diffaug.py da4e9834e767ce2d unverified MIT (permissive)
DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation 30 May 2023 KU-CVLAB/DaRF/plenoxels/models/discriminator.py 2e499d784aa6bc3c unverified MIT (permissive)
TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation 26 Apr 2023 gnobitab/FuseDream/DiffAugment_pytorch.py 0be77ca193f97b78 unverified MIT (permissive)
FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations 2 Feb 2023 a514514772/fedlap-dp/utils/augmentation.py 6e636dbbdcaa0f16 unverified MIT (permissive)
Private Set Generation with Discriminative Information 7 Nov 2022 DingfanChen/Private-Set/utils/augmentation.py 96c702388fb2fc5b unverified MIT (permissive)
Outpainting by Queries 12 Jul 2022 Kaiseem/QueryOTR/models/DiffAug.py b0bbabd6de30f612 ran · fixture could not drive it fingerprinted Apache-2.0 (permissive)
Augmentation-Aware Self-Supervision for Data-Efficient GAN Training 31 May 2022 liang-hou/augself-gan/augself-biggan/DiffAugment_pytorch.py 37e1e70fdd71c5ac unverified MIT (permissive)
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference 15 Apr 2022 hushell/pmf_cvpr22/models/utils.py 98235a49e66df4c8 unverified Apache-2.0 (permissive)
SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image 2 Apr 2022 VITA-Group/SinNeRF/models/diff_aug.py d39b74f30fd860ba unverified MIT (permissive)
CAFE: Learning to Condense Dataset by Aligning Features 3 Mar 2022 kaiwang960112/cafe/distill.py de12e346f3744454 ran · fixture could not drive it no licence file found · pointer only
Ensembling Off-the-shelf Models for GAN Training 16 Dec 2021 nupurkmr9/vision-aided-gan/vision_aided_loss/DiffAugment_pytorch.py 1d566d068b0ed0af unverified MIT (permissive)
Projected GANs Converge Faster 1 Nov 2021 dome272/ProjectedGAN-pytorch/projected_gan.py fb73f5657d3d5dfd ran MIT (permissive)
Projected GANs Converge Faster 1 Nov 2021 autonomousvision/projected_gan/pg_modules/discriminator.py fb2ae62e229d8e49 ran · fixture could not drive it fingerprinted MIT (permissive)
Regularizing Generative Adversarial Networks under Limited Data 7 Apr 2021 identical code first harvested elsewhere b0bbabd6de30f612 ran · fixture could not drive it fingerprinted licence of this copy not recorded
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 mit-han-lab/data-efficient-gans/DiffAugment_pytorch.py b0bbabd6de30f612 ran · fixture could not drive it fingerprinted BSD-2-Clause (permissive)
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 mit-han-lab/data-efficient-gans/DiffAugment_pytorch.py 5a98bf7c8a33d10d ran · fixture could not drive it fingerprinted BSD-2-Clause (permissive)
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 VITA-Group/Ultra-Data-Efficient-GAN-Training/BigGAN and DiffAugGAN/utils/diff_aug.py b13ee69651d4b880 ran · fixture could not drive it MIT (permissive)
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 milmor/self-supervised-gan/diffaug.py 106e066ecaa411cb ran · fixture could not drive it fingerprinted MIT (permissive)
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 eps696/stylegan2/src/training/DiffAugment_tf.py 719b769b10895fa0 ran · fixture could not drive it fingerprinted licence not identified · pointer only
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 milmor/TransGAN/diffaug.py 9f13704fe37f3a7f ran · fixture could not drive it fingerprinted MIT (permissive)
Differentiable Augmentation for Data-Efficient GAN Training 18 Jun 2020 claim-berlin/3d_stylegan_circle_of_willis/diff_augment.py aff3959c75a4b707 ran · our draft was wrong licence not identified · pointer only
Analyzing and Improving the Image Quality of StyleGAN 3 Dec 2019 Di-Is/stylegan2-ada-pytorch/stylegan2_pytorch/diff_augment.py 737fe4ff1cef5f47 unverified MIT (permissive)
Analyzing and Improving the Image Quality of StyleGAN 3 Dec 2019 lucidrains/stylegan2-pytorch/stylegan2_pytorch/diff_augment.py 688410c911dd9bc7 unverified MIT (permissive)
arXiv:aaai_29065 UBCDingXin/Dual-NDA/SteeringAngle/SteeringAngle_128x128/CcGAN/NDA/DiffAugment_pytorch.py 1d566d068b0ed0af unverified MIT (permissive)
arXiv:Ni_CHAIN_Enhancing_Generalization_in_Data-Efficient_GANs_via_lipsCHitz_continuity_constrAIned_CVPR_2024_paper MaxwellYaoNi/CHAIN/FastGANDBig/diffaug.py a167a40e94a5e80d unverified MIT (permissive)
arXiv:136830137 hkust-vgd/neural_scene_decoration/lightweight_gan/diff_augment.py b3877afdaafbe50f unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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