arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10764cs.CV
收藏

双端一致性模型

Dual-End Consistency Model

Zhejiang University(浙江大学);Bytedance Inc.(字节跳动公司);Zhejiang Lab(浙江实验室)

Linwei Dong, Ruoyu Guo, Ge Bai, Zehuan Yuan, Yawei Luo, Changqing Zou

AI总结:

本文提出双端一致性模型,通过选择关键子轨迹集群解决训练不稳定和采样灵活性问题,实现稳定高效的生成。

摘要:

缓慢的迭代采样性质仍然是扩散和基于流的生成模型实际部署的主要瓶颈。尽管一致性模型(CMs)代表了基于蒸馏的高效生成方法的最新状态,但其大规模应用仍受两个关键问题的限制:训练不稳定和采样灵活性不足。现有方法通过架构调整或正则化目标来缓解这些问题,却忽略了轨迹选择的重要性。在本文中,我们首先分析了这两个限制:训练不稳定源于不稳定自监督项引起的损失发散,而采样灵活性不足源于误差累积。基于这些见解和分析,我们提出了双端一致性模型(DE-CM),选择关键子轨迹集群以实现稳定和有效的训练。DE-CM将PF-ODE轨迹分解并选择三个关键子轨迹作为优化目标。具体而言,我们的方法利用连续时间CMs目标实现少步蒸馏,并利用流匹配作为边界正则化器以稳定训练过程。此外,我们提出了一种新的噪声到噪声(N2N)映射,可以将噪声映射到任何点,从而减轻第一步的误差累积。广泛的实验结果表明了我们方法的有效性:在ImageNet 256x256数据集上的一步生成中,它实现了最先进的FID分数为1.70,优于现有基于CM的一步方法。

英文摘要:

The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While consistency models (CMs) represent a state-of-the-art distillation-based approach for efficient generation, their large-scale application is still limited by two key issues: training instability and inflexible sampling. Existing methods seek to mitigate these problems through architectural adjustments or regularized objectives, yet overlook the critical reliance on trajectory selection. In this work, we first conduct an analysis on these two limitations: training instability originates from loss divergence induced by unstable self-supervised term, whereas sampling inflexibility arises from error accumulation. Based on these insights and analysis, we propose the Dual-End Consistency Model (DE-CM) that selects vital sub-trajectory clusters to achieve stable and effective training. DE-CM decomposes the PF-ODE trajectory and selects three critical sub-trajectories as optimization targets. Specifically, our approach leverages continuous-time CMs objectives to achieve few-step distillation and utilizes flow matching as a boundary regularizer to stabilize the training process. Furthermore, we propose a novel noise-to-noisy (N2N) mapping that can map noise to any point, thereby alleviating the error accumulation in the first step. Extensive experimental results show the effectiveness of our method: it achieves a state-of-the-art FID score of 1.70 in one-step generation on the ImageNet 256x256 dataset, outperforming existing CM-based one-step approaches.

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。

↑