提出新型生成模型，一步生成且训练更稳定，性能超越现有方法。
Adversarial Flow Models
- 结合对抗与流模型优势，直接学习确定性噪声到数据映射。
- 在相同计算量下，112层模型单步生成FID达1.94，创最佳纪录。
- 无需中间监督，支持超深网络端到端训练，适合高精度生成任务。
我们提出对抗流模型（Adversarial Flow Models），一种兼具对抗与流模型特性的生成模型。该方法支持原生的一步或多步生成，并通过对抗目标进行训练。与传统GAN不同，其生成器被鼓励学习确定性的噪声到数据映射，显著提升了对抗训练的稳定性。与基于一致性的方法相比，本模型直接学习一步或少数几步生成，无需学习概率流的中间时间步，从而保留模型容量并避免误差累积。在ImageNet-256px上，相同1NFE设置下，我们的B/2模型性能接近一致性方法的XL/2模型；而我们的XL/2模型达到新最优的FID 2.38。此外，我们实现了56层和112层模型的端到端训练，无需中间监督，分别仅用一次前向传播即取得FID 2.08和1.94，超越对应28层2NFE和4NFE模型，在同等算力和参数量下表现更优。代码已开源。
原文摘要 · Abstract (English)
We present adversarial flow models, a class of generative models that belongs to both the adversarial and flow families. Our method supports native one-step and multi-step generation and is trained with an adversarial objective. Unlike traditional GANs, in which the generator learns an arbitrary transport map between the noise and data distributions, our generator is encouraged to learn a deterministic noise-to-data mapping. This significantly stabilizes adversarial training. Unlike consistency-based methods, our model directly learns one-step or few-step generation without having to learn the intermediate timesteps of the probability flow for propagation. This preserves model capacity 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 achieves a new best FID of 2.38. We additionally demonstrate end-to-end training of 56-layer and 112-layer models without any intermediate supervision, achieving FIDs of 2.08 and 1.94 with a single forward pass and surpassing the corresponding 28-layer 2NFE and 4NFE counterparts with equal compute and parameters. The code is available at https://github.com/ByteDance-Seed/Adversarial-Flow-Models
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。