# Few-shot Image Generation with Mixup-based Distance Learning

arXiv: https://arxiv.org/abs/2111.11672 · HTML: https://mlsanity.com/paper/2111.11672/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 58 references that are in the map.
- First posted on arXiv 23 Nov 2021.

## Builds on (most cited first, 30 of 43)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [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)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [High-Fidelity GAN Inversion for Image Attribute Editing](https://mlsanity.com/paper/2109.06590/) (2021)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (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)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (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)
- [One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1706.00826/) (2017)

## Built on by (most cited first, 16 of 16)

- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions](https://mlsanity.com/paper/2402.17065/) (2024)
- [Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis](https://mlsanity.com/paper/2409.17439/) (2024)
- [Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2407.06136/) (2024)
- [Generating Progressive Images from Pathological Transitions via Diffusion Model](https://mlsanity.com/paper/2311.12316/) (2023)
- [Smoothness Similarity Regularization for Few-Shot GAN Adaptation](https://mlsanity.com/paper/2308.09717/) (2023)
- [BlendGAN: Learning and Blending the Internal Distributions of Single Images by Spatial Image-Identity Conditioning](https://mlsanity.com/paper/2212.01589/) (2022)
- [Analyzing Multimodal Objectives Through the Lens of Generative Diffusion Guidance](https://mlsanity.com/paper/2302.10305/) (2023)
- [Few-shot Image Generation via Information Transfer from the Built Geodesic Surface](https://mlsanity.com/paper/2401.01749/) (2024)
- [Rare event modeling with self-regularized normalizing flows: what can we learn from a single failure?](https://mlsanity.com/paper/2502.21110/) (2025)
- [Conservative Generator, Progressive Discriminator: Coordination of Adversaries in Few-shot Incremental Image Synthesis](https://mlsanity.com/paper/2207.14491/) (2022)
- [Few-shot Face Image Translation via GAN Prior Distillation](https://mlsanity.com/paper/2301.12257/) (2023)
- [ConcatPlexer: Additional Dim1 Batching for Faster ViTs](https://mlsanity.com/paper/2308.11199/) (2023)
- [Fashion Style Editing with Generative Human Prior](https://mlsanity.com/paper/2404.01984/) (2024)

## Abstract (arXiv)

Producing diverse and realistic images with generative models such as GANs typically requires large scale training with vast amount of images. GANs trained with limited data can easily memorize few training samples and display undesirable properties like "stairlike" latent space where interpolation in the latent space yields discontinuous transitions in the output space. In this work, we consider a challenging task of pretraining-free few-shot image synthesis, and seek to train existing generative models with minimal overfitting and mode collapse. We propose mixup-based distance regularization on the feature space of both a generator and the counterpart discriminator that encourages the two players to reason not only about the scarce observed data points but the relative distances in the feature space they reside. Qualitative and quantitative evaluation on diverse datasets demonstrates that our method is generally applicable to existing models to enhance both fidelity and diversity under few-shot setting. Code is available.