Methods › Computer Vision › Adversarial Image Data Augmentation › DiffAugment

DiffAugment

3 papers tagged archive 2025-07-28

Introduced by Shengyu Zhao et al. in Differentiable Augmentation for Data-Efficient GAN Training

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

Differentiable Augmentation (DiffAugment) is a set of differentiable image transformations used to augment data during GAN training. The transformations are applied to the real and generated images. It enables the gradients to be propagated through the augmentation back to the generator, regularizes the discriminator without manipulating the target distribution, and maintains the balance of training dynamics. Three choices of transformation are preferred by the authors in their experiments: Translation, CutOut, and Color.

PaperSourceSee Code · mit-han-lab/data-efficient-gans

Papers archive 2025-07-28

3 shown of 3, 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

6 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
Data Augmentation1
Image Generation1
Medical Image Generation1
Object1
Relation1
Triplet1

Usage over time archive 2025-07-28

Papers per year tagged with DiffAugment: 2020 to 2024, peak 1 1 0 2020: 1 paper 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 1 paper 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (3 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

Adversarial Image Data AugmentationAdversarial Training

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