# Benchmarking Learnt Radio Localisation under Distribution Shift

arXiv: https://arxiv.org/abs/2210.01930 · HTML: https://mlsanity.com/paper/2210.01930/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Channel Charting: Locating Users within the Radio Environment using Channel State Information](https://mlsanity.com/paper/1807.05247/) (2018)
- [Novel Massive MIMO Channel Sounding Data Applied to Deep Learning-based Indoor Positioning](https://mlsanity.com/paper/1810.04126/) (2018)
- [On Deep Learning-based Massive MIMO Indoor User Localization](https://mlsanity.com/paper/1804.04826/) (2018)
- [CSI-based Outdoor Localization for Massive MIMO: Experiments with a Learning Approach](https://mlsanity.com/paper/1806.07447/) (2018)
- [WiCluster: Passive Indoor 2D/3D Positioning using WiFi without Precise Labels](https://mlsanity.com/paper/2107.01002/) (2021)
- [Neural RF SLAM for unsupervised positioning and mapping with channel state information](https://mlsanity.com/paper/2203.08264/) (2022)
- [Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization](https://mlsanity.com/paper/2111.12175/) (2021)
- [Probabilistic 5G Indoor Positioning Proof of Concept with Outlier Rejection](https://mlsanity.com/paper/2207.08512/) (2022)

## Built on by (most cited first, 1 of 1)

- [Neural 5G Indoor Localization with IMU Supervision](https://mlsanity.com/paper/2402.09948/) (2024)

## Abstract (arXiv)

Deploying radio frequency (RF) localisation systems invariably entails non-trivial effort, particularly for the latest learning-based breeds. There has been little prior work on characterising and comparing how learnt localiser networks can be deployed in the field under real-world RF distribution shifts. In this paper, we present RadioBench: a suite of 8 learnt localiser nets from the state-of-the-art to study and benchmark their real-world deployability, utilising five novel industry-grade datasets. We train 10k models to analyse the inner workings of these learnt localiser nets and uncover their differing behaviours across three performance axes: (i) learning, (ii) proneness to distribution shift, and (iii) localisation. We use insights gained from this analysis to recommend best practices for the deployability of learning-based RF localisation under practical constraints.