Paper ID: 2209.04517 • Published Sep 9, 2022

Affinity-VAE for disentanglement, clustering and classification of objects in multidimensional image data

Jola Mirecka, Marjan Famili, Anna Kotańska, Nikolai Juraschko, Beatriz Costa-Gomes, Colin M. Palmer, Jeyan Thiyagalingam, Tom...
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
In this work we present affinity-VAE: a framework for automatic clustering and classification of objects in multidimensional image data based on their similarity. The method expands on the concept of β-VAEs with an informed similarity-based loss component driven by an affinity matrix. The affinity-VAE is able to create rotationally-invariant, morphologically homogeneous clusters in the latent representation, with improved cluster separation compared with a standard β-VAE. We explore the extent of latent disentanglement and continuity of the latent spaces on both 2D and 3D image data, including simulated biological electron cryo-tomography (cryo-ET) volumes as an example of a scientific application.