对抗性流模型

摘要

我们提出对抗性流模型，这是一类融合对抗模型与流模型的生成模型。该方法支持原生单步或多步生成，并采用对抗目标进行训练。与传统GAN中生成器学习噪声分布与数据分布间任意传输方案不同，我们的生成器学习确定性噪声-数据映射，这与流匹配模型中的最优传输方式一致，从而显著提升了对抗训练的稳定性。同时，区别于基于一致性的方法，我们的模型直接学习单步或少步生成，无需学习概率流传播的中间时间步，这节省了模型容量、减少了训练迭代次数并避免了误差累积。在ImageNet-256px数据集相同1NFE设置下，我们的B/2模型性能接近基于一致性的XL/2模型，而我们的XL/2模型更是创造了2.38 FID的新纪录。我们还展示了通过深度重复实现56层和112层模型端到端训练的可能性，在无需任何中间监督的情况下，单次前向传播即可分别达到2.08和1.94的FID，超越了对应的2NFE和4NFE模型性能。

English

We present adversarial flow models, a class of generative models that unifies adversarial models and flow models. Our method supports native one-step or multi-step generation and is trained using the adversarial objective. Unlike traditional GANs, where the generator learns an arbitrary transport plan between the noise and the data distributions, our generator learns a deterministic noise-to-data mapping, which is the same optimal transport as in flow-matching models. This significantly stabilizes adversarial training. Also, unlike consistency-based methods, our model directly learns one-step or few-step generation without needing to learn the intermediate timesteps of the probability flow for propagation. This saves model capacity, reduces training iterations, and avoids error accumulation. Under the same 1NFE setting on ImageNet-256px, our B/2 model approaches the performance of consistency-based XL/2 models, while our XL/2 model creates a new best FID of 2.38. We additionally show the possibility of end-to-end training of 56-layer and 112-layer models through depth repetition without any intermediate supervision, and achieve FIDs of 2.08 and 1.94 using a single forward pass, surpassing their 2NFE and 4NFE counterparts.

对抗性流模型

Adversarial Flow Models

摘要

Support