---
title: "Dual-VaDE: Efficient and Robust Prototype Learning via Variational Dual-Domain Mixture Priors"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05099v1"
permalink: "https://feed.astralor.com/items/itm_e552c9816d375b4d2fcc39a7"
published: "2026-11-03T15:54:14.000Z"
score: 57
channel: "tech"
tags: ["推理效率","Dual-VaDE","Efficient","Robust Prototype Learning","Variational Dual-Domain Mixture","Priors"]
---

# Dual-VaDE: Efficient and Robust Prototype Learning via Variational Dual-Domain Mixture Priors

## 速览

In this paper, we propose Dual-VaDE, an unsupervised generative framework for learning interpretable anatomical prototypes from unlabeled medical images. In contrast to previous variational methods that rely on a single…

## 关键点

- In this paper, we propose Dual-VaDE, an unsupervised generative framework for learning interpretable anatomical prototypes from unlabeled medical images.
- In contrast to previous variational methods that rely on a single spatial latent code, which often entangles global geometry with local textures and fails to capture their cross-domain dependencies, Dual-VaDE introduces…
- We derive an exact, closed-form variational lower bound that fuses this joint prior into the decoder and optimizes the entire network end-to-end via an alternating EM formulation, avoiding heuristic two-stage clustering…

## 全文

In this paper, we propose Dual-VaDE, an unsupervised generative framework for learning interpretable anatomical prototypes from unlabeled medical images. In contrast to previous variational methods that rely on a single spatial latent code, which often entangles global geometry with local textures and fails to capture their cross-domain dependencies, Dual-VaDE introduces a dual-domain Gaussian mixture prior that explicitly couples spatial anatomy with phase-preserving Fourier spectral representations. We derive an exact, closed-form variational lower bound that fuses this joint prior into the decoder and optimizes the entire network end-to-end via an alternating EM formulation, avoiding heuristic two-stage clustering while ensuring superior training stability and robustness. Evaluated on OASIS-3 brain MRI, Dual-VaDE delivers substantially sharper and more plausible prototypes, achieves superior cluster separation with improvements of up to 94% over spatial-only baselines, exhibits markedly reduced variance across random seeds, and incurs negligible inference overhead (0.28 ms per image).

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e552c9816d375b4d2fcc39a7