Immiscible Color Flows in Optimal Transport Networks for Image Classification
arXiv:2205.02938 · doi:10.3389/fphy.2023.1089114
Abstract
In classification tasks, it is crucial to meaningfully exploit the information contained in data. While much of the work in addressing these tasks is devoted to building complex algorithmic infrastructures to process inputs in a black-box fashion, less is known about how to exploit the various facets of the data, before inputting this into an algorithm. Here, we focus on this latter perspective, by proposing 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. The resulting optimal flows can then be fed into standard classifiers to distinguish images in different classes. We show how our method can outperform competing approaches on image classification tasks in datasets where color information matters.
arXiv comment23 pages, 13 figures, 2 tables
References in corpus (12)
- Damage and fluctuations induce loops in optimal transport networks
- Optimal protocols and optimal transport in stochastic thermodynamics
- Fluctuations and redundancy in optimal transport networks
- Global Optimization, Local Adaptation, and the Role of Growth in Distribution Networks
- An optimal transport formulation of the Einstein equations of general relativity
- Discontinuous transition to loop formation in optimal supply networks
- Optimal transport in multilayer networks for traffic flow optimization
- Network extraction by routing optimization
- Designing optimal networks for multi-commodity transport problem
- Sustainable optimal transport in multilayer networks
- Multicommodity routing optimization for engineering networks
- Principled network extraction from images