基于扩散的原生对抗合成以增强医学分割泛化
Diffusion-Based Native Adversarial Synthesis for Enhanced Medical Segmentation Generalization
把扩散模型的初始噪声当作可优化变量来挖掘「原生对抗样本」，无需重训或改动扩散模型即可生成难例做数据增强；做医学分割或任何小样本分割任务时，这是一个可直接套用的合成增强插件。
原文依据 optimizes the initial noise to mine natively adversarial samples without modifying or retraining the diffusion model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散模型（DMs）能够生成解剖学上逼真的医学图像，为通过合成数据增强提升泛化能力提供了一条颇具吸引力的途径。然而，高视觉逼真度并不必然转化为下游效用的提升。本文针对扩散驱动增强中的两个关键问题展开研究。第一，应当合成什么？我们表明，合成对抗性，即合成样本所诱导的期望经验损失，是泛化的关键驱动因素。更重要的是，只有源自扩散模型分布所支持的困难样本的原生对抗性才能带来一致的增益，而由基于攻击的扰动所诱导的人工对抗性则是有害的。第二，此类样本应当如何合成？我们提出了对抗性挖掘器（Adversariality Miner），这是一个轻量级模块，通过优化初始噪声来挖掘原生对抗样本，且无需修改或重新训练扩散模型。在多种扩散骨干网络与医学基准上的大量实验证实了本方法的有效性，为扩散驱动的泛化建立了一条有原则的路径。
英文原文摘要 1153 字符
Diffusion models (DMs) can generate anatomically realistic medical images, offering a compelling route to improving generalization through synthetic augmentation. Yet high visual realism does not necessarily translate into improved downstream utility. This work addresses two key questions in diffusion-driven augmentation. First, what should be synthesized? We show that synthetic adversariality, namely the expected empirical loss induced by synthetic samples, is a key driver of generalization. More importantly, only native adversariality, arising from hard examples supported by the diffusion model distribution, yields consistent gains, whereas artificial adversariality induced by attack-based perturbations is detrimental. Second, how should such samples be synthesized? We propose the Adversariality Miner, a lightweight module that optimizes the initial noise to mine natively adversarial samples without modifying or retraining the diffusion model. Extensive experiments across diverse diffusion backbones and medical benchmarks confirm the effectiveness of our approach, establishing a principled path toward diffusion-driven generalization.