Immiscible Color Flows in Optimal Transport Networks for Image Classification

05/04/2022
by   Alessandro Lonardi, et al.
6

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.

READ FULL TEXT

page 11

page 12

page 14

page 15

research
05/29/2019

Solving graph compression via optimal transport

We propose a new approach to graph compression by appeal to optimal tran...
research
09/19/2018

Dynamical Optimal Transport on Discrete Surfaces

We propose a technique for interpolating between probability distributio...
research
09/23/2012

Image Classification and Optimized Image Reproduction

By taking into account the properties and limitations of the human visua...
research
07/11/2023

Decorrelation using Optimal Transport

Being able to decorrelate a feature space from protected attributes is a...
research
03/11/2021

The Location of Optimal Object Colors with More Than Two Transitions

The chromaticity diagram associated with the CIE 1931 color matching fun...
research
02/01/2019

ColorNet: Investigating the importance of color spaces for image classification

Image classification is a fundamental application in computer vision. Re...
research
02/09/2021

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

MetaDL Challenge 2020 focused on image classification tasks in few-shot ...

Please sign up or login with your details

Forgot password? Click here to reset