Organizing Unstructured Image Collections using Natural Language

arXiv (Preprint)

Mingxuan Liu1, Zhun Zhong3, Jun Li5, Gianni Franchi4, Subhankar Roy1, Elisa Ricci1,2
1University of Trento, 2Fondazione Bruno Kessler, 3Hefei University of Technology, 4U2IS, ENSTA Paris, Institut Polytechnique de Paris, 5Technical University of Munich, Munich Center for Machine Learning
Paper arXiv Demo (work in progress) Code (coming soon) Data (coming soon)

TL;DR: We introduce and explore the task of Semantic Multiple Clustering with the goal of automatically discovering grouping criteria from large image collections and uncovering corresponding interpretable substructures without relying on human input.