arXiv cs.AI· Amin Golnari, Saeid Sanei·· 14 小时前AI 评分18
StaX-Net：面向跨模态医学图像翻译的 Stackelberg 交错非对称网络
StaX-Net: Stackelberg Interleaved Asymmetric Network for Cross-Modality Medical Image Translation
AI 导读
StaX-Net 是一种用于跨模态医学图像翻译的 Stackelberg 交错非对称网络，通过部分耦合的编码器-判别器结构与 2D FAST 层，在学习使用特权信息范式下蒸馏目标监督先验。
正文 · 原文
Abstract:Cross-modality medical image translation is challenged by anatomically inconsistent synthesis that can compromise clinical diagnosis. We propose StaX-Net, a Stackelberg interleaved asymmetric network that incorporates a partially coupled encoder-discriminator structure, and a 2D feature aggregation and spatial transformation (FAST) layer that distills target-supervised priors under the learning using privileged information paradigm. The shared blocks between the generator and discriminator enhance architectural feature alignment. To stabilize the leader-follower training, a Stackelberg-inspired asymmetric optimization scheme employs explicit shared-parameter freezing and asymmetric learning rates. The FAST layer distills target-domain priors during training and applies a source-only transform at inference. This constrains the synthesis process through target-informed feature representations relative to standard generative architectures. The code is available on GitHub for public use.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34214 [cs.CV] |
| (or arXiv:2610.34214v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34214 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Amin Golnari [view email]
[v1]
Sun, 25 Oct 2026 11:01:19 UTC (8,685 KB)
来源：arXiv cs.AI · arxiv.org