# Data-Efficient Instance Generation from Instance Discrimination

arXiv: https://arxiv.org/abs/2106.04566 · HTML: https://mlsanity.com/paper/2106.04566/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 58 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 30 of 41)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [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)
- [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)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [Large Scale Adversarial Representation Learning](https://mlsanity.com/paper/1907.02544/) (2019)

## Built on by (most cited first, 30 of 58)

- [Diffusion-GAN: Training GANs with Diffusion](https://mlsanity.com/paper/2206.02262/) (2022)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)
- [Ensembling Off-the-shelf Models for GAN Training](https://mlsanity.com/paper/2112.09130/) (2021)
- [A Closer Look at Few-shot Image Generation](https://mlsanity.com/paper/2205.03805/) (2022)
- [One-Shot Generative Domain Adaptation](https://mlsanity.com/paper/2111.09876/) (2021)
- [Diffusion Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2212.04473/) (2022)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [MyStyle: A Personalized Generative Prior](https://mlsanity.com/paper/2203.17272/) (2022)
- [Towards a Scalable Reference-Free Evaluation of Generative Models](https://mlsanity.com/paper/2407.02961/) (2024)
- [Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning](https://mlsanity.com/paper/2310.12952/) (2023)
- [Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks](https://mlsanity.com/paper/2207.08736/) (2022)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (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)
- [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)
- [Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling](https://mlsanity.com/paper/2305.18375/) (2023)
- [FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs](https://mlsanity.com/paper/2207.08630/) (2022)
- [Efficient Image Generation with Variadic Attention Heads](https://mlsanity.com/paper/2211.05770/) (2022)
- [An Interpretable Evaluation of Entropy-based Novelty of Generative Models](https://mlsanity.com/paper/2402.17287/) (2024)
- [FreGAN: Exploiting Frequency Components for Training GANs under Limited Data](https://mlsanity.com/paper/2210.05461/) (2022)
- [KD-DLGAN: Data Limited Image Generation via Knowledge Distillation](https://mlsanity.com/paper/2303.17158/) (2023)
- [Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach](https://mlsanity.com/paper/2405.02700/) (2024)
- [Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms](https://mlsanity.com/paper/2412.17622/) (2024)
- [Domain Expansion of Image Generators](https://mlsanity.com/paper/2301.05225/) (2023)
- [NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs](https://mlsanity.com/paper/2304.05866/) (2023)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work typically employs data augmentation to mitigate the overfitting of the discriminator yet still learn the discriminator with a bi-classification (i.e., real vs. fake) task. In this work, we propose a data-efficient Instance Generation (InsGen) method based on instance discrimination. Concretely, besides differentiating the real domain from the fake domain, the discriminator is required to distinguish every individual image, no matter it comes from the training set or from the generator. In this way, the discriminator can benefit from the infinite synthesized samples for training, alleviating the overfitting problem caused by insufficient training data. A noise perturbation strategy is further introduced to improve its discriminative power. Meanwhile, the learned instance discrimination capability from the discriminator is in turn exploited to encourage the generator for diverse generation. Extensive experiments demonstrate the effectiveness of our method on a variety of datasets and training settings. Noticeably, on the setting of 2K training images from the FFHQ dataset, we outperform the state-of-the-art approach with 23.5% FID improvement.