Domain-Factored Untrained Deep Prior for Spectrum Cartography

TL;DR

This paper introduces a novel spectrum cartography method using untrained neural networks that captures radio map structures without training data, achieving performance comparable to trained models.

Contribution

It proposes a domain-factored untrained neural network approach for spectrum cartography, reducing data requirements and addressing distribution shift issues.

Findings

Achieves comparable performance to trained deep generative models

Reduces sample complexity in spectrum cartography

Operates without training data, handling distribution shifts effectively

Abstract

Spectrum cartography (SC) focuses on estimating the radio power propagation map of multiple emitters across space and frequency using limited sensor measurements. Recent advances in SC have shown that leveraging learned deep generative models (DGMs) as structural constraints yields state-of-the-art performance. By harnessing the expressive power of neural networks, these structural "priors" capture intricate patterns in radio maps. However, training DGMs requires substantial data, which is not always available, and distribution shifts between training and testing data can further degrade performance. To address these challenges, this work proposes using untrained neural networks (UNNs) for SC. UNNs, commonly applied in vision tasks to represent complex data without training, encode structural information of data in neural architectures. In our approach, a custom-designed UNN represents radio maps under a spatio-spectral domain factorization model, leveraging physical characteristics to reduce sample complexity of SC. Experiments show that the method achieves performance comparable to learned DGM-based SC, without requiring training data.