# High-Fidelity Image Generation With Fewer Labels

arXiv: https://arxiv.org/abs/1903.02271 · HTML: https://mlsanity.com/paper/1903.02271/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2019.

## Built on by (most cited first, 30 of 52)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Return of Unconditional Generation: A Self-supervised Representation Generation Method](https://mlsanity.com/paper/2312.03701/) (2023)
- [Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective](https://mlsanity.com/paper/2408.06741/) (2024)
- [Is Attention Better Than Matrix Decomposition?](https://mlsanity.com/paper/2109.04553/) (2021)
- [Self-supervised learning methods and applications in medical imaging analysis: A survey](https://mlsanity.com/paper/2109.08685/) (2021)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [High Fidelity Visualization of What Your Self-Supervised Representation Knows About](https://mlsanity.com/paper/2112.09164/) (2021)
- [What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels](https://mlsanity.com/paper/2103.04400/) (2021)
- [Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models](https://mlsanity.com/paper/2403.01639/) (2024)
- [Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training](https://mlsanity.com/paper/2305.13689/) (2023)
- [Self-Distilled StyleGAN: Towards Generation from Internet Photos](https://mlsanity.com/paper/2202.12211/) (2022)
- [Self-Guided Diffusion Models](https://mlsanity.com/paper/2210.06462/) (2022)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification](https://mlsanity.com/paper/2111.06399/) (2021)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [Progressive Open Space Expansion for Open-Set Model Attribution](https://mlsanity.com/paper/2303.06877/) (2023)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning](https://mlsanity.com/paper/2403.07240/) (2024)
- [Class Balancing GAN with a Classifier in the Loop](https://mlsanity.com/paper/2106.09402/) (2021)
- [Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection](https://mlsanity.com/paper/2403.06803/) (2024)
- [MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation](https://mlsanity.com/paper/2401.11115/) (2024)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation](https://mlsanity.com/paper/2302.08366/) (2023)
- [Model Extraction and Defenses on Generative Adversarial Networks](https://mlsanity.com/paper/2101.02069/) (2021)
- [Improved Input Reprogramming for GAN Conditioning](https://mlsanity.com/paper/2201.02692/) (2022)
- [Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments](https://mlsanity.com/paper/2012.02527/) (2020)

## Abstract (arXiv)

Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images at high resolution, they rely on a vast quantity of labeled data. In this work we demonstrate how one can benefit from recent work on self- and semi-supervised learning to outperform the state of the art on both unsupervised ImageNet synthesis, as well as in the conditional setting. In particular, the proposed approach is able to match the sample quality (as measured by FID) of the current state-of-the-art conditional model BigGAN on ImageNet using only 10% of the labels and outperform it using 20% of the labels.