Immiscible Color Flows in Optimal Transport Networks for Image Classification

Abstract

In classification tasks, it is crucial to meaningfully exploit information contained in data. Here, we propose a physics-inspired dynamical system that adapts Optimal Transport principles to effectively leverage color distributions of images. Our dynamics regulates immiscible fluxes of colors traveling on a network built from images. Instead of aggregating colors together, it treats them as different commodities that interact with a shared capacity on edges. Our method outperforms competitor algorithms on image classification tasks in datasets where color information matters.

Publication
Submitted
Alessandro Lonardi
Alessandro Lonardi
PhD student

The main focus of my current research is studying routing problems combining approaches stemming from optimal transport and belief propagation. In particular, I am interested in understanding how different route selection mechanisms affect traffic and total path length of networks. The applications of my work span from urban to biological networks. Previously I was a Master’s Student in Mathematical Engineering at UniPd (Padua, Italy), where I also obtained my Bachelor’s degree in Physics.

Diego Baptista Theuerkauf
Diego Baptista Theuerkauf
PhD student

My research focuses on analising graph-based approximations of solutions of optimal transportation problems. We use biologically-inspired models to find transport plans for many different routing frameworks.

Caterina De Bacco
Caterina De Bacco
CyberValley Research Group Leader

My research focuses on understanding, optimizing and predicting relations between the microscopic and macroscopic properties of complex large-scale interacting systems.

Related