Shape complexity estimation using VAE Article Swipe

PDF

Related Concepts

Computer science Exploit Computational complexity theory Code (set theory) Estimation Algorithm Artificial intelligence Machine learning Pattern recognition (psychology) Set (abstract data type) Computer security Programming language Management Economics

Markus Rothgaenger , Andrew Melnik , Helge Ritter ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2304.02766 · OA: W4362705797

In this paper, we compare methods for estimating the complexity of two-dimensional shapes and introduce a method that exploits reconstruction loss of Variational Autoencoders with different sizes of latent vectors. Although complexity of a shape is not a well defined attribute, different aspects of it can be estimated. We demonstrate that our methods captures some aspects of shape complexity. Code and training details will be publicly available.

Keywords: Computer science · Exploit · Computational complexity theory · Code (set theory) · Estimation · Algorithm · Artificial intelligence · Machine learning · Pattern recognition (psychology) · Set (abstract data type)