# Few-shot Image Generation via Masked Discrimination

arXiv: https://arxiv.org/abs/2210.15194 · HTML: https://mlsanity.com/paper/2210.15194/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 27 Oct 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (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)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [Toward Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1711.11586/) (2017)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [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)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [MineGAN: effective knowledge transfer from GANs to target domains with few images](https://mlsanity.com/paper/1912.05270/) (2019)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [Image Augmentations for GAN Training](https://mlsanity.com/paper/2006.02595/) (2020)
- [Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks](https://mlsanity.com/paper/2110.08398/) (2021)
- [Few-Shot Adaptation of Generative Adversarial Networks](https://mlsanity.com/paper/2010.11943/) (2020)
- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)

## Built on by (most cited first, 12 of 12)

- [Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation](https://mlsanity.com/paper/2408.13509/) (2024)
- [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Domain Re-Modulation for Few-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2302.02550/) (2023)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [DreamCinema: Cinematic Transfer with Free Camera and 3D Character](https://mlsanity.com/paper/2408.12601/) (2024)
- [A Review on Generative AI For Text-To-Image and Image-To-Image Generation and Implications To Scientific Images](https://mlsanity.com/paper/2502.21151/) (2025)
- [Few-shot 3D Shape Generation](https://mlsanity.com/paper/2305.11664/) (2023)
- [DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning](https://mlsanity.com/paper/2411.04571/) (2024)
- [Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations](https://mlsanity.com/paper/2405.14857/) (2024)
- [Hyperspectral Image Generation with Unmixing Guided Diffusion Model](https://mlsanity.com/paper/2506.02601/) (2025)
- [AIR: Zero-shot Generative Model Adaptation with Iterative Refinement](https://mlsanity.com/paper/2506.10895/) (2025)

## Abstract (arXiv)

Few-shot image generation aims to generate images of high quality and great diversity with limited data. However, it is difficult for modern GANs to avoid overfitting when trained on only a few images. The discriminator can easily remember all the training samples and guide the generator to replicate them, leading to severe diversity degradation. Several methods have been proposed to relieve overfitting by adapting GANs pre-trained on large source domains to target domains using limited real samples. This work presents a novel approach to realize few-shot GAN adaptation via masked discrimination. Random masks are applied to features extracted by the discriminator from input images. We aim to encourage the discriminator to judge various images which share partially common features with training samples as realistic. Correspondingly, the generator is guided to generate diverse images instead of replicating training samples. In addition, we employ a cross-domain consistency loss for the discriminator to keep relative distances between generated samples in its feature space. It strengthens global image discrimination and guides adapted GANs to preserve more information learned from source domains for higher image quality. The effectiveness of our approach is demonstrated both qualitatively and quantitatively with higher quality and greater diversity on a series of few-shot image generation tasks than prior methods.