用于无监督潜在语义发现的 Householder 投影器
Householder Projector for Unsupervised Latent Semantics Discovery
AI总结：
本文提出基于 Householder 变换的低秩正交 Householder Projector，用以参数化潜在代码到特征的投影矩阵，使预训练 StyleGAN2/StyleGAN3 能以极少微调发现更解耦、精确且不损失保真度的语义方向。
摘要：
生成对抗网络（GANs），尤其是近期基于风格的生成器（StyleGANs），在结构化潜在空间中具有丰富多样的语义。潜在语义发现方法应运而生，它们通过在潜在代码中移动，使遍历过程中只有一个因素发生变化。最近，一种无监督方法提出了一个有前景的方向：直接将把潜在代码映射到特征的投影矩阵的特征向量用作可解释方向。然而，一个被忽视的事实是，该投影矩阵是非正交的，而且特征向量数量过大。非正交性会使前几个特征向量中的语义属性发生纠缠，而即使矩阵是正交的，高维度也可能导致各方向之间出现无意义的变化。为避免这些问题，我们提出 Householder Projector，这是一种基于 Householder 变换的灵活且通用的低秩正交矩阵表示，用于参数化投影矩阵。正交性保证特征向量对应于解耦的可解释语义，而低秩特性则促使每个识别出的方向都具有有意义的变化。我们将该投影器集成到预训练的 StyleGAN2/StyleGAN3 中，并在多个基准上评估模型。仅使用原始训练步数 1% 以内的微调，我们的投影器就能帮助 StyleGANs 发现更加解耦和精确的语义属性，同时不牺牲图像保真度。
英文摘要：
Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space. Latent semantics discovery methods emerge to move around the latent code such that only one factor varies during the traversal. Recently, an unsupervised method proposed a promising direction to directly use the eigenvectors of the projection matrix that maps latent codes to features as the interpretable directions. However, one overlooked fact is that the projection matrix is non-orthogonal and the number of eigenvectors is too large. The non-orthogonality would entangle semantic attributes in the top few eigenvectors, and the large dimensionality might result in meaningless variations among the directions even if the matrix is orthogonal. To avoid these issues, we propose Householder Projector, a flexible and general low-rank orthogonal matrix representation based on Householder transformations, to parameterize the projection matrix. The orthogonality guarantees that the eigenvectors correspond to disentangled interpretable semantics, while the low-rank property encourages that each identified direction has meaningful variations. We integrate our projector into pre-trained StyleGAN2/StyleGAN3 and evaluate the models on several benchmarks. Within only $1\%$ of the original training steps for fine-tuning, our projector helps StyleGANs to discover more disentangled and precise semantic attributes without sacrificing image fidelity.
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。
