结构化状态空间正则化用于生成友好的图像标记化
Structured State-Space Regularization for Generation-Friendly Image Tokenization
AI总结:
本文提出结构化状态空间正则化方法,通过诱导潜在空间的频谱结构提升图像标记化生成性能,同时保持重建保真度。
摘要:
图像标记器在现代生成模型中起着核心作用,其中潜在空间的结构关键决定了下游生成性能。有效潜在表示的一个关键但未被充分探索的特性是频谱组织,即能够跨频率组件编码信息。在本文中,我们引入了结构化状态空间正则化,一种系统诱导潜在空间频谱结构的方法。我们通过重新审视状态空间模型(SSMs)作为模仿基函数行为的系统,推导出一个正则化目标。这种视角揭示了SSMs的隐藏状态被诱导以捕捉频率组件,从而产生一种新的正则器,强制潜在空间捕捉图像的频谱结构。实验表明,我们的正则器在提升图像标记器生成性能的同时,仅导致微小的重建保真度损失。
英文摘要:
Image tokenizers play a central role in modern generative models, where the structure of the latent space critically determines the downstream generation performance. A key but underexplored property of effective latent representations is spectral organization, the ability to encode information across frequency components. In this work, we introduce structured state-space regularization, a principled approach to inducing spectral structure in latent spaces. We derive a regularization objective by revisiting state-space models (SSMs) as systems mimicking a basis function's behavior. This perspective reveals that hidden states of SSMs are induced to capture the frequency components, resulting in a novel regularizer that enforces the latent space to capture spectral structure of images. Experiments demonstrate that our regularizer improves the generative performance of image tokenizers while incurring only minimal loss in their reconstruction 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。