# Augmentation-Aware Self-Supervision for Data-Efficient GAN Training

arXiv: https://arxiv.org/abs/2205.15677 · HTML: https://mlsanity.com/paper/2205.15677/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 31 May 2022.

## Builds on (most cited first, 30 of 40)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)
- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Consistency Regularization for Generative Adversarial Networks](https://mlsanity.com/paper/1910.12027/) (2019)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs](https://mlsanity.com/paper/2002.10964/) (2020)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [MineGAN: effective knowledge transfer from GANs to target domains with few images](https://mlsanity.com/paper/1912.05270/) (2019)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [Self-Supervised GANs via Auxiliary Rotation Loss](https://mlsanity.com/paper/1811.11212/) (2018)
- [Ensembling Off-the-shelf Models for GAN Training](https://mlsanity.com/paper/2112.09130/) (2021)
- [Image Augmentations for GAN Training](https://mlsanity.com/paper/2006.02595/) (2020)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [Improving Transferability of Representations via Augmentation-Aware Self-Supervision](https://mlsanity.com/paper/2111.09613/) (2021)
- [Training GANs with Stronger Augmentations via Contrastive Discriminator](https://mlsanity.com/paper/2103.09742/) (2021)

## Built on by (most cited first, 7 of 7)

- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition](https://mlsanity.com/paper/2404.19527/) (2024)
- [CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization](https://mlsanity.com/paper/2404.00521/) (2024)
- [MITA: Bridging the Gap between Model and Data for Test-time Adaptation](https://mlsanity.com/paper/2410.09398/) (2024)
- [Score Augmentation for Diffusion Models](https://mlsanity.com/paper/2508.07926/) (2025)
- [Subjective Face Transform using Human First Impressions](https://mlsanity.com/paper/2309.15381/) (2023)
- [A Self-Supervised Task for Fault Detection in Satellite Multivariate Time Series](https://mlsanity.com/paper/2407.02861/) (2024)

## Abstract (arXiv)

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs.