# Image Generation From Small Datasets via Batch Statistics Adaptation

arXiv: https://arxiv.org/abs/1904.01774 · HTML: https://mlsanity.com/paper/1904.01774/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 30 of 102)

- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Regularizing Generative Adversarial Networks under Limited Data](https://mlsanity.com/paper/2104.03310/) (2021)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [Ensembling Off-the-shelf Models for GAN Training](https://mlsanity.com/paper/2112.09130/) (2021)
- [Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation](https://mlsanity.com/paper/2303.02389/) (2023)
- [DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions](https://mlsanity.com/paper/2403.17827/) (2024)
- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)
- [A Closer Look at Few-shot Image Generation](https://mlsanity.com/paper/2205.03805/) (2022)
- [UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation](https://mlsanity.com/paper/2203.02557/) (2022)
- [One-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2111.09876/) (2021)
- [Sketch Your Own GAN](https://mlsanity.com/paper/2108.02774/) (2021)
- [Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification](https://mlsanity.com/paper/2111.06399/) (2021)
- [Diffusion Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2212.04473/) (2022)
- [Few-shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2210.16559/) (2022)
- [DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model](https://mlsanity.com/paper/2211.16374/) (2022)
- [One-Shot Adaptation of GAN in Just One CLIP](https://mlsanity.com/paper/2203.09301/) (2022)
- [Zero-shot Generative Model Adaptation via Image-specific Prompt Learning](https://mlsanity.com/paper/2304.03119/) (2023)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [Collapse by Conditioning: Training Class-conditional GANs with Limited Data](https://mlsanity.com/paper/2201.06578/) (2022)
- [Rewriting Geometric Rules of a GAN](https://mlsanity.com/paper/2207.14288/) (2022)
- [Few-shot Image Generation with Diffusion Models](https://mlsanity.com/paper/2211.03264/) (2022)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [Generalized One-shot Domain Adaptation of Generative Adversarial Networks](https://mlsanity.com/paper/2209.03665/) (2022)
- [HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks](https://mlsanity.com/paper/2210.08884/) (2022)
- [Exploring Incompatible Knowledge Transfer in Few-shot Image Generation](https://mlsanity.com/paper/2304.07574/) (2023)

## Abstract (arXiv)

Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the amount of data required, we propose a new method for transferring prior knowledge of the pre-trained generator, which is trained with a large dataset, to a small dataset in a different domain. Using such prior knowledge, the model can generate images leveraging some common sense that cannot be acquired from a small dataset. In this work, we propose a novel method focusing on the parameters for batch statistics, scale and shift, of the hidden layers in the generator. By training only these parameters in a supervised manner, we achieved stable training of the generator, and our method can generate higher quality images compared to previous methods without collapsing, even when the dataset is small (~100). Our results show that the diversity of the filters acquired in the pre-trained generator is important for the performance on the target domain. Our method makes it possible to add a new class or domain to a pre-trained generator without disturbing the performance on the original domain.