Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations

04/15/2022
by   Michael Poli, et al.
5

Many patterns in nature exhibit self-similarity: they can be compactly described via self-referential transformations. Said patterns commonly appear in natural and artificial objects, such as molecules, shorelines, galaxies and even images. In this work, we investigate the role of learning in the automated discovery of self-similarity and in its utilization for downstream tasks. To this end, we design a novel class of implicit operators, Neural Collages, which (1) represent data as the parameters of a self-referential, structured transformation, and (2) employ hypernetworks to amortize the cost of finding these parameters to a single forward pass. We investigate how to leverage the representations produced by Neural Collages in various tasks, including data compression and generation. Neural Collages image compressors are orders of magnitude faster than other self-similarity-based algorithms during encoding and offer compression rates competitive with implicit methods. Finally, we showcase applications of Neural Collages for fractal art and as deep generative models.

READ FULL TEXT

page 1

page 7

page 8

page 10

page 22

page 23

page 24

research
12/08/2021

Implicit Neural Representations for Image Compression

Recently Implicit Neural Representations (INRs) gained attention as a no...
research
06/08/2021

Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations

Deep generative models have emerged as a powerful tool for learning info...
research
02/11/2021

Text Compression-aided Transformer Encoding

Text encoding is one of the most important steps in Natural Language Pro...
research
01/30/2022

COIN++: Data Agnostic Neural Compression

Neural compression algorithms are typically based on autoencoders that r...
research
06/28/2023

DUET: 2D Structured and Approximately Equivariant Representations

Multiview Self-Supervised Learning (MSSL) is based on learning invarianc...
research
08/18/2023

Data Compression and Inference in Cosmology with Self-Supervised Machine Learning

The influx of massive amounts of data from current and upcoming cosmolog...

Please sign up or login with your details

Forgot password? Click here to reset