VeCoR -- 速度对比正则化用于流匹配
VeCoR -- Velocity Contrastive Regularization for Flow Matching
AI总结：
VeCoR通过引入速度对比正则化，提升流匹配模型的稳定性与生成质量，尤其在低步数和轻量级设置中表现优异。
摘要：
流匹配（FM）最近出现作为扩散模型的一种原则性且高效的替代方法。标准FM鼓励学习到的速度场遵循目标方向；然而，它可能在轨迹上积累误差并推动样本离开数据流形，导致感知退化，尤其是在轻量或低步数配置中。\n为了增强稳定性和泛化能力，我们将FM扩展为一个平衡的吸引-排斥方案，该方案提供了明确的指导，即“去哪里”和“不去哪里”。正式来说，我们提出了速度对比正则化（VeCoR），一种用于基于流的生成模型的补充训练方案，它在标准FM目标中加入了对比、双侧监督。VeCoR不仅将预测速度与稳定的参考方向对齐（正监督），还将其推离不一致、离流形的方向（负监督）。这种对比性形式将FM从纯粹吸引、单侧目标转变为双侧训练信号，规范轨迹演变，并在不同数据集和模型架构上提高感知保真度。\n在ImageNet-1K 256×256上，VeCoR在SiT-XL/2和REPA-SiT-XL/2模型上分别实现了22%和35%的相对FID减少，并在MS-COCO文本到图像生成中进一步获得FID提升（32%的相对提升），显示出在稳定、收敛和图像质量方面的一致改进，特别是在低步数和轻量级设置中。项目页面：https://p458732.github.io/VeCoR_Project_Page/
英文摘要：
Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target direction; however, it may accumulate errors along the trajectory and drive samples off the data manifold, leading to perceptual degradation, especially in lightweight or low-step configurations. To enhance stability and generalization, we extend FM into a balanced attract-repel scheme that provides explicit guidance on both "where to go" and "where not to go." To be formal, we propose \textbf{Velocity Contrastive Regularization (VeCoR)}, a complementary training scheme for flow-based generative modeling that augments the standard FM objective with contrastive, two-sided supervision. VeCoR not only aligns the predicted velocity with a stable reference direction (positive supervision) but also pushes it away from inconsistent, off-manifold directions (negative supervision). This contrastive formulation transforms FM from a purely attractive, one-sided objective into a two-sided training signal, regularizing trajectory evolution and improving perceptual fidelity across datasets and backbones. On ImageNet-1K 256$\times$256, VeCoR yields 22\% and 35\% relative FID reductions on SiT-XL/2 and REPA-SiT-XL/2 backbones, respectively, and achieves further FID gains (32\% relative) on MS-COCO text-to-image generation, demonstrating consistent improvements in stability, convergence, and image quality, particularly in low-step and lightweight settings. Project page: https://p458732.github.io/VeCoR_Project_Page/
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。
