# The Comparability of Model Fusion to Measured Data in Confuser Rejection

arXiv: https://arxiv.org/abs/2505.00836 · HTML: https://mlsanity.com/paper/2505.00836/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel](https://mlsanity.com/paper/2010.15110/) (2020)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning](https://mlsanity.com/paper/2001.01425/) (2020)
- [On The Distribution of Penultimate Activations of Classification Networks](https://mlsanity.com/paper/2107.01900/) (2021)

## Built on by (most cited first, 2 of 2)

- [Online Sparse Synthetic Aperture Radar Imaging](https://mlsanity.com/paper/2603.08582/) (2026)
- [Online CS-based SAR Edge-Mapping](https://mlsanity.com/paper/2604.19989/) (2026)

## Abstract (arXiv)

Data collection has always been a major issue in the modeling and training of large deep learning networks, as no dataset can account for every slight deviation we might see in live usage. Collecting samples can be especially costly for Synthetic Aperture Radar (SAR), limiting the amount of unique targets and operating conditions we are able to observe from. To counter this lack of data, simulators have been developed utilizing the shooting and bouncing ray method to allow for the generation of synthetic SAR data on 3D models. While effective, the synthetically generated data does not perfectly correlate to the measured data leading to issues when training models solely on synthetic data. We aim to use computational power as a substitution for this lack of quality measured data, by ensembling many models trained on synthetic data. Synthetic data is also not complete, as we do not know what targets might be present in a live environment. Therefore we need to have our ensembling techniques account for these unknown targets by applying confuser rejection in which our models will reject unknown targets it is presented with, and only classify those it has been trained on.