SCFlow：通过流模型隐式学习风格与内容解耦
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
AI总结：
SCFlow通过流匹配框架学习风格与内容的可逆合并，无需显式解耦监督，在合成数据集上训练后零样本泛化至ImageNet-1k和WikiArt，实现自然涌现的解耦。
摘要：
在视觉模型中显式解耦风格和内容仍然具有挑战性，原因是它们在语义上重叠且人类感知具有主观性。现有方法通过生成性或判别性目标提出分离，但仍面临解耦相互交织概念的内在模糊性。相反，我们提出疑问：能否通过以可逆方式学习合并风格和内容，使分离自然涌现，从而绕过显式解耦？我们提出SCFlow，一种流匹配框架，学习纠缠表示与解耦表示之间的双向映射。我们的方法基于三个关键见解：1）仅训练以合并风格和内容这一明确定义的任务，即可在无显式监督的情况下实现可逆解耦；2）流匹配可桥接任意分布，避免了扩散模型和归一化流的限制性高斯先验；3）构建了一个包含510,000个样本的合成数据集（51种风格×10,000个内容样本），通过系统的风格-内容配对模拟解耦。除了可控生成任务外，我们证明SCFlow在零样本设置下泛化到ImageNet-1k和WikiArt，并取得有竞争力的性能，突显解耦自然地从可逆合并过程中涌现。
英文摘要：
Explicitly disentangling style and content in vision models remains challenging due to their semantic overlap and the subjectivity of human perception. Existing methods propose separation through generative or discriminative objectives, but they still face the inherent ambiguity of disentangling intertwined concepts. Instead, we ask: Can we bypass explicit disentanglement by learning to merge style and content invertibly, allowing separation to emerge naturally? We propose SCFlow, a flow-matching framework that learns bidirectional mappings between entangled and disentangled representations. Our approach is built upon three key insights: 1) Training solely to merge style and content, a well-defined task, enables invertible disentanglement without explicit supervision; 2) flow matching bridges on arbitrary distributions, avoiding the restrictive Gaussian priors of diffusion models and normalizing flows; and 3) a synthetic dataset of 510,000 samples (51 styles $\times$ 10,000 content samples) was curated to simulate disentanglement through systematic style-content pairing. Beyond controllable generation tasks, we demonstrate that SCFlow generalizes to ImageNet-1k and WikiArt in zero-shot settings and achieves competitive performance, highlighting that disentanglement naturally emerges from the invertible merging process.
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。
