Persistence Forcing：利用像素空间扩散中的特征特化
原标题：Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion
AI 摘要
该论文提出在像素空间扩散 Transformer（DiT）中引入异构细化（heterogeneous refinement），为不同特征组分配不同的细化预算，从而自然涌现出「持久特征」与「活跃特征」的分化：持久特征编码全局结构，活跃特征专注高频细节。基于此提出 Persistence Forcing（PerF），让持久特征持续条件化活跃特征的细化过程，并在采样阶段引入 Persistence Guidance（PG）以补充无分类器引导（CFG）。在 ImageNet 上，PerF 在多个模型规模上降低了 FID，PerF-H/32 进一步取得更优 FID 与 Inception Score。
正文节选
Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion Abstract Pixel-space diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden representations typically undergo uniform refinement across depth. Natural images, however, are inherently organized at different levels of granularity. Global structure can often be represented compactly, whereas local textures and fine details require richer representations. Motivated by this, we in