arXiv：cs.LG· Simon Penninga, Ruud van Sloun·· 3 小时前AI 评分31
Deep Bayesian REFoCUS：用深度生成先验求解超声多基地贝叶斯逆问题
Deep Bayesian REFoCUS
AI 导读
研究者提出 Deep Bayesian REFoCUS，将任意发射序列下的超声多基地恢复建模为贝叶斯推理问题，并训练深度生成先验以应对经典线性 REFoCUS 解码器失效的秩亏情形。该方法在所有秩亏程度与噪声水平下均优于线性基线，且在逆问题精确时可回归线性解码，并能在采集零空间中表达不确定性，而线性解码器仅给出点估计。研究还分析了仿真与在体采集间的分布偏移，显示无需微调或适配即具备泛化能力。
正文
Abstract:In this work we formulate ultrasound multistatic recovery from arbitrary transmit sequences as a Bayesian inference problem. To that end, we train a deep generative prior on multistatic data sets to tackle the rank-deficient regime in which classical linear REFoCUS decoders fail. This appproach, which we term Deep Bayesian REFoCUS, outperforms the linear baselines for all regimes of rank-deficiency and noise levels, and regresses to linear decoding when inversion is exact. The model also expresses uncertainty in the null space of the acquisitions, whereas the linear REFoCUS decoders only provide point estimates. Finally, we analyze the impact of distribution shift between simulation and in-vivo acquisitions, showing remarkable generalization ability without any fine-tuning or adaptation.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03419 [cs.LG] |
| (or arXiv:2610.03419v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03419 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Simon Penninga [view email]
[v1]
Fri, 2 Oct 2026 15:06:30 UTC (4,302 KB)
来源：arXiv：cs.LG · arxiv.org