mlsanityData to 7 Oct 2026

Learning Fractals by Gradient Descent

arXiv 2303.12722 ↗First posted 14 Mar 2023cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this property to create random fractal images for model pre-training. In this paper, we study the inverse problem -- given a target image (not necessarily a fractal), we aim to generate a fractal image that looks like it. We propose a novel approach that learns the parameters underlying a fractal image via gradient descent. We show that our approach can find fractal parameters of high visual quality and be compatible with different loss functions, opening up several potentials, e.g., learning fractals for downstream tasks, scientific understanding, etc.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 59 references that are in the map. First posted on arXiv 14 Mar 2023.

Builds on

23 of 59 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 655
  7. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 562
  8. 2018Deep Learning for Classical Japanese Literaturecited by 415
  9. 2021GAN Inversion: A Surveycited by 366
  10. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  11. 2018Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layerscited by 340
  12. 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
11 more
  1. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  2. 2021Pre-training without Natural Imagescited by 100
  3. 2021Learning to See by Looking at Noisecited by 92
  4. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  5. 2021Can Vision Transformers Learn without Natural Images?cited by 32
  6. 2021Improving Fractal Pre-trainingcited by 26
  7. 2021Fractal Structure and Generalization Properties of Stochastic Optimization Algorithmscited by 23
  8. 2019Expression of Fractals Through Neural Network Functionscited by 8
  9. 2022Self-Similarity Priors: Neural Collages as Differentiable Fractal Representationscited by 6
  10. 2021Fractal Pyramid Networkscited by 2
  11. 2021Beyond Flatland: Pre-training with a Strong 3D Inductive Biascited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Learning with Mandelbrot and Juliacited by 0
  2. 2026Amortized Set Prediction for Inverse IFS Reconstruction from Density Mapscited by 0