从SRA到Self-Flow：数据增强还是自我监督？

摘要

表示对齐已成为加速扩散变换器训练并提升生成质量的有效方法。最近的自我对齐方法（如SRA和Self-Flow）通过构建扩散模型内部的自身对齐，进一步消除了对外部预训练编码器的依赖。然而，SRA到Self-Flow的改进机制——即双时间步调度——仍未得到充分检验：Self-Flow将其增益归因于不同噪声级别下token之间的交互，其中更干净的token有助于推断更嘈杂的token。在本工作中，我们重新审视这一解释，并探究该增益是否实际上源自沿噪声维度的数据增强。为解耦这些因素，我们引入了注意力分离（Attention Separation），该方法在保留Self-Flow中相同双时间步输入的同时，阻断分配给不同噪声级别的token之间的注意力。令人惊讶的是，移除这种交互并不会降低性能，甚至可能提升性能，这表明从SRA到Self-Flow的改进主要源于数据增强。此外，我们证明注意力分离本身通过将单个图像拆分为多个有效的训练部分来扩展训练数据，从而提供了一种增强效果。基于这些观察，我们将自我表示对齐与双时间步和注意力分离增强相结合，并在ImageNet上展示了该设计的有效性。

English

Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself. However, the mechanism behind the improvement from SRA to Self-Flow, dual-time scheduling, remains under-examined: Self-Flow attributes its gain to interactions between tokens at different noise levels, where cleaner tokens help infer noisier ones. In this work, we revisit this explanation and ask whether the gain instead comes from data augmentation along the noise dimension. To disentangle these factors, we introduce Attention Separation, which preserves the same dual-timestep input as Self-Flow while blocking attention between tokens assigned to different noise levels. Surprisingly, removing such interaction does not degrade performance and can even improve it, suggesting that the improvement from SRA to Self-Flow mainly comes from data augmentation. Furthermore,We show that Attention Separation itself provides an augmentation effect by splitting a single image into multiple effective training parts to expand the training data. Based on these observations, we combine self-representation alignment with dual-timestep and attention-separation augmentation, and demonstrate the effectiveness of this design on ImageNet.