让条件生成更清晰：通过对比学习增强流匹配的区分度
Contrastive Flow Matching
- 引入对比损失，强制不同条件下的生成路径互不重叠
- 训练速度提升最高达9倍，去噪步数减少5倍，FID降低8.9
- 适合需要高精度条件控制的图像生成任务
无条件流匹配通过确保样本对间的流唯一性来训练扩散模型，将数据从源分布转移到目标分布。但在条件设置（如类别条件模型）下，这种唯一性无法保证——不同条件的流可能重叠，导致生成结果模糊。本文提出对比流匹配（Contrastive Flow Matching），在原有流匹配目标基础上增加对比项，显式最大化任意样本对间预测流的差异性，增强条件分离能力。我们在多种模型架构上对分类条件（ImageNet-1k）和文本到图像（CC3M）任务进行了广泛实验。结果表明，使用对比流匹配训练模型可实现：（1）训练速度最高提升9倍；（2）所需去噪步骤最多减少5倍；（3）FID得分最低降低8.9。代码已开源：https://github.com/gstoica27/DeltaFM.git。
原文摘要 · Abstract (English)
Unconditional flow-matching trains diffusion models to transport samples from a source distribution to a target distribution by enforcing that the flows between sample pairs are unique. However, in conditional settings (e.g., class-conditioned models), this uniqueness is no longer guaranteed--flows from different conditions may overlap, leading to more ambiguous generations. We introduce Contrastive Flow Matching, an extension to the flow matching objective that explicitly enforces uniqueness across all conditional flows, enhancing condition separation. Our approach adds a contrastive objective that maximizes dissimilarities between predicted flows from arbitrary sample pairs. We validate Contrastive Flow Matching by conducting extensive experiments across varying model architectures on both class-conditioned (ImageNet-1k) and text-to-image (CC3M) benchmarks. Notably, we find that training models with Contrastive Flow Matching (1) improves training speed by a factor of up to 9x, (2) requires up to 5x fewer de-noising steps and (3) lowers FID by up to 8.9 compared to training the same models with flow matching. We release our code at: https://github.com/gstoica27/DeltaFM.git.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。