通过慢速插值混合缓解扩散模型训练测试偏差问题
MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
- 利用慢速插值混合提升预测网络在各训练步的鲁棒性
- 在ImageNet上实现1.10~1.55的FID，优于现有方法
- 适合需要高质量图像生成的研究者与开发者
本文研究扩散模型中的训练-测试差异（即暴露偏差）问题。训练时，预测网络在某一时刻的输入是噪声与真实数据的插值结果，而测试时输入为生成的噪声数据。为此提出名为MixFlow的新训练方法，其灵感源于慢流现象：在采样时刻，最接近生成噪声数据的真实插值对应更高噪声的时间步（称为慢速时间步），即真实时间步晚于采样时间步。MixFlow利用这些慢速时间步的插值组合（慢速插值混合）对每个训练时间步的预测网络进行后训练。在类别条件图像生成（包括SiT、REPA和RAE）及文生图任务上的实验验证了该方法的有效性。在RAE模型上，无引导条件下，256×256分辨率下获得1.43 FID，512×512下为1.55；有引导条件下，两者均为1.10。
原文摘要 · Abstract (English)
This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data that is an interpolation of the noise and the data, and during testing, the input is the generated noisy data. We present a novel training approach, named MixFlow, for improving the performance. Our approach is motivated by the Slow Flow phenomenon: the ground-truth interpolation that is the nearest to the generated noisy data at a given sampling timestep is observed to correspond to a higher-noise timestep (termed slowed timestep), i.e., the corresponding ground-truth timestep is slower than the sampling timestep. MixFlow leverages the interpolations at the slowed timesteps, named slowed interpolation mixture, for post-training the prediction network for each training timestep. Experiments over class-conditional image generation (including SiT, REPA, and RAE) and text-to-image generation validate the effectiveness of our approach. Our approach MixFlow over the RAE models achieve strong generation results on ImageNet: 1.43 FID (without guidance) and 1.10 (with guidance) at 256 x 256, and 1.55 FID (without guidance) and 1.10 (with guidance) at 512 x 512.
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。