# Meta Internal Learning

arXiv: https://arxiv.org/abs/2110.02900 · HTML: https://mlsanity.com/paper/2110.02900/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [The Expressive Power of Neural Networks: A View from the Width](https://mlsanity.com/paper/1709.02540/) (2017)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://mlsanity.com/paper/1708.05344/) (2017)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Approximating Continuous Functions by ReLU Nets of Minimal Width](https://mlsanity.com/paper/1710.11278/) (2017)
- [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](https://mlsanity.com/paper/1601.04589/) (2016)
- [Learning feed-forward one-shot learners](https://mlsanity.com/paper/1606.05233/) (2016)
- [ResNet with one-neuron hidden layers is a Universal Approximator](https://mlsanity.com/paper/1806.10909/) (2018)
- [Improved Techniques for Training Single-Image GANs](https://mlsanity.com/paper/2003.11512/) (2020)
- [Stochastic Hyperparameter Optimization through Hypernetworks](https://mlsanity.com/paper/1802.09419/) (2018)
- [Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks](https://mlsanity.com/paper/1610.09887/) (2016)
- [Deep Meta Functionals for Shape Representation](https://mlsanity.com/paper/1908.06277/) (2019)
- [HyperGAN: A Generative Model for Diverse, Performant Neural Networks](https://mlsanity.com/paper/1901.11058/) (2019)
- [Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample](https://mlsanity.com/paper/2006.12226/) (2020)
- [On Infinite-Width Hypernetworks](https://mlsanity.com/paper/2003.12193/) (2020)

## Built on by (most cited first, 7 of 7)

- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks](https://mlsanity.com/paper/2207.08736/) (2022)
- [Magnitude Invariant Parametrizations Improve Hypernetwork Learning](https://mlsanity.com/paper/2304.07645/) (2023)
- [Neuro-Symbolic Learning: Principles and Applications in Ophthalmology](https://mlsanity.com/paper/2208.00374/) (2022)
- [Neural Inverse Kinematics](https://mlsanity.com/paper/2205.10837/) (2022)
- [One-Shot Synthesis of Images and Segmentation Masks](https://mlsanity.com/paper/2209.07547/) (2022)
- [Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions](https://mlsanity.com/paper/2301.04605/) (2023)

## Abstract (arXiv)

Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. Since these models are trained on a single image, they are limited in their scale and application. To overcome these issues, we propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. In the presented meta-learning approach, a single-image GAN model is generated given an input image, via a convolutional feedforward hypernetwork f. This network is trained over a dataset of images, allowing for feature sharing among different models, and for interpolation in the space of generative models. The generated single-image model contains a hierarchy of multiple generators and discriminators. It is therefore required to train the meta-learner in an adversarial manner, which requires careful design choices that we justify by a theoretical analysis. Our results show that the models obtained are as suitable as single-image GANs for many common image applications, significantly reduce the training time per image without loss in performance, and introduce novel capabilities, such as interpolation and feedforward modeling of novel images.