DeepAI AI Chat
Log In Sign Up

Immiscible Color Flows in Optimal Transport Networks for Image Classification

by   Alessandro Lonardi, et al.

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.


page 11

page 12

page 14

page 15


Solving graph compression via optimal transport

We propose a new approach to graph compression by appeal to optimal tran...

Dynamical Optimal Transport on Discrete Surfaces

We propose a technique for interpolating between probability distributio...

Image Classification and Optimized Image Reproduction

By taking into account the properties and limitations of the human visua...

Decorrelation using Optimal Transport

Being able to decorrelate a feature space from protected attributes is a...

The Location of Optimal Object Colors with More Than Two Transitions

The chromaticity diagram associated with the CIE 1931 color matching fun...

ColorNet: Investigating the importance of color spaces for image classification

Image classification is a fundamental application in computer vision. Re...

Code Repositories


MODI is an algorithm implementing a multicommodity optimal transport-based dynamics for image classification

view repo