MD-Face: 基于MoE的无标签解耦表示用于交互式面部属性编辑
MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing
AI总结：
MD-Face提出一种基于MoE的无标签解耦表示框架，通过动态专家分配机制和几何感知损失提升面部属性编辑效果，实验显示其在图像质量和推理延迟方面优于扩散方法。
摘要：
基于GAN的面部属性编辑广泛应用于虚拟化身和社会媒体，但常面临属性纠缠问题，即修改一个面部属性会意外改变其他属性。虽然监督解耦表示学习可以解决这一问题，但依赖大量标注数据，导致高标注成本。为此，我们提出MD-Face，一种基于MoE的无标签解耦表示学习框架。MD-Face利用具有门控机制的MoE主干网络，动态分配专家，使模型能学习更独立的语义向量。为进一步增强属性解耦，我们引入几何感知损失，通过Jacobian-based pushforward方法将每个语义向量对齐其对应的语义边界向量（SBV）。实验表明，MD-Face在ProGAN和StyleGAN上的表现优于无监督基线，并与监督方法竞争。与基于扩散的方法相比，它在图像质量和推理延迟方面表现更优，使其成为交互式编辑的理想选择。
英文摘要：
GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one face attribute unintentionally alters others. While supervised disentangled representation learning can address this, it relies heavily on labeled data, incurring high annotation costs. To address these challenges, we propose MD-Face, a label-free disentangled representation learning framework based on Mixture of Experts (MoE). MD-Face utilizes a MoE backbone with a gating mechanism that dynamically allocates experts, enabling the model to learn semantic vectors with greater independence. To further enhance attribute entanglement, we introduce a geometry-aware loss, which aligns each semantic vector with its corresponding Semantic Boundary Vector (SBV) through a Jacobian-based pushforward method. Experiments with ProGAN and StyleGAN show that MD-Face outperforms unsupervised baselines and competes with supervised ones. Compared to diffusion-based methods, it offers better image quality and lower inference latency, making it ideal for interactive editing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
