MedDiME：用于医学反事实生成的自适应掩码高效潜在扩散
MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual Generation
- Technical University of Denmark（丹麦技术大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对医学反事实生成中扩散方法速度慢、内存高及掩码不兼容问题，提出MedDiME潜在扩散框架，采用梯度驱动自适应掩码，实现40倍加速和13倍内存降低。
AI中文摘要：
医学反事实生成通过修改图像来改变模型预测，以实现可解释性。然而，现有的基于扩散的方法通常速度过慢且内存密集，使其难以应用于高分辨率场景。此外，现有的掩码策略与像素空间表示紧密耦合，无法与潜在空间扩散编辑兼容。为解决这些挑战，我们提出了MedDiME，一种潜在空间分类器引导的扩散框架，在降低计算和内存开销的同时，引入了一种与潜在空间兼容、基于梯度驱动的自适应掩码机制，用于空间精确的医学反事实生成。大量实验表明，与先前的分类器引导扩散基线相比，MedDiME实现了高质量的反事实生成和显著的效率提升，推理速度最高提升40倍，峰值GPU内存使用降低13倍。
英文摘要：
Medical counterfactual generation modifies images to change model predictions for interpretability. However, existing diffusion-based approaches are often prohibitively slow and memory-intensive, making them difficult to apply in high-resolution settings. Moreover, existing masking strategies are tightly coupled with pixel-space representations, making them incompatible with latent-space diffusion editing. To address these challenges, we propose MedDiME, a latent-space classifier-guided diffusion framework that reduces computational and memory overhead while introducing a latent-compatible, gradient-driven adaptive masking mechanism for spatially precise medical counterfactual generation. Extensive experiments demonstrate that MedDiME achieves high-quality counterfactual generation with significant efficiency gains compared to prior classifier-guided diffusion baselines, achieving up to 40 times faster inference and 13 times lower peak GPU memory usage.
