解耦解耦表征：通过扩散模型改进潜在单元
Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
AI总结：
针对无监督解耦表征学习中扩散模型应用探索有限的问题，提出动态高斯锚定和跳跃丢弃技术，提升潜在单元独立性与模型适配性，实现最优解耦性能及下游任务优势。
摘要：
解耦表征学习（DRL）旨在将观测数据分解为核心内在因素，以实现对数据的深度理解。在真实场景中，手动定义和标注这些因素并非易事，这使得无监督方法颇具吸引力。近年来，对于将已成为生成建模主流的扩散模型（DMs）用于无监督DRL的探索较为有限。这类方法引入自身的归纳偏置，以确保输入到DM的每个潜在单元仅表达一个独特因素。在此背景下，我们设计了动态高斯锚定（Dynamic Gaussian Anchoring）方法，以强制实现属性分离的潜在单元，从而获得更具可解释性的DRL。这种非常规归纳偏置明确划定了属性之间的决策边界，同时也提升了潜在单元之间的独立性。此外，我们还提出了跳跃丢弃（Skip Dropout）技术，该技术可轻松修改去噪U-Net使其更适配DRL，解决了其与解耦特征提取器不兼容的问题。我们的方法充分考虑了潜在单元语义和DM的独特结构，提升了基于DM的解耦表征的实用性，在合成数据和真实数据上均展现了当前最优的解耦性能，同时在下游任务中也具备优势。
英文摘要：
Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making unsupervised methods attractive. Recently, there have been limited explorations of utilizing diffusion models (DMs), which are already mainstream in generative modeling, for unsupervised DRL. They implement their own inductive bias to ensure that each latent unit input to the DM expresses only one distinct factor. In this context, we design Dynamic Gaussian Anchoring to enforce attribute-separated latent units for more interpretable DRL. This unconventional inductive bias explicitly delineates the decision boundaries between attributes while also promoting the independence among latent units. Additionally, we also propose Skip Dropout technique, which easily modifies the denoising U-Net to be more DRL-friendly, addressing its uncooperative nature with the disentangling feature extractor. Our methods, which carefully consider the latent unit semantics and the distinct DM structure, enhance the practicality of DM-based disentangled representations, demonstrating state-of-the-art disentanglement performance on both synthetic and real data, as well as advantages in downstream tasks.
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。
