Self-Similarity Priors: Neural Collages as Differentiable Fractal RepresentationsDownload PDF

Published: 31 Oct 2022, Last Modified: 13 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: implicit representations, compression, deep equilibrium models, generative models, fractal, fixed-point
Abstract: 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 detail how to leverage the representations produced by Neural Collages in various tasks, including data compression and generation. Neural Collage 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.
TL;DR: We present a class of implicit models -- Neural Collages -- that extract self-similarity in data as sets of parameters of a contraction operator.
Supplementary Material: pdf
13 Replies

Loading