提出反射式优化目标，有效缓解流匹配中的暴露偏差问题。
ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
- 设计动态修正机制，通过训练时调度采样调整偏差输入的预测目标。
- 在CelebA-64上使FID降低35.65%，显著提升生成质量。
- 无需修改模型结构，适配所有流匹配框架，通用性强。
尽管近期进展显著，流匹配方法仍受训练与推理阶段不一致导致的暴露偏差影响。本文分析其根源：(1) 训练中模型未学习对偏差输入的泛化能力；(2) 早期去噪过程缺乏低频信息，造成偏差累积。基于此，提出 ReflexFlow，一种简单有效的反射式学习目标修正方法。该方法包含两部分：(1) 反向漂移校正（ADR），利用训练时调度采样重新设计损失函数，动态调整偏差输入的预测目标；(2) 频率补偿（FC），通过重加权损失来弥补缺失的低频成分。ReflexFlow 兼容所有流匹配框架，且不依赖具体模型结构。在 CIFAR-10、CelebA-64 与 ImageNet-256 上实验表明，其有效缓解暴露偏差，在 CelebA-64 上实现 35.65% 的 FID 降低。
原文摘要 · Abstract (English)
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model lacks generalization to biased inputs during training, and (2) insufficient low-frequency content captured during early denoising, leading to accumulated bias. Based on these insights, we propose ReflexFlow, a simple and effective reflexive refinement of the Flow Matching learning objective that dynamically corrects exposure bias. ReflexFlow consists of two components: (1) Anti-Drift Rectification (ADR), which reflexively adjusts prediction targets for biased inputs utilizing a redesigned loss under training-time scheduled sampling; and (2) Frequency Compensation (FC), which reflects on missing low-frequency components and compensates them by reweighting the loss using exposure bias. ReflexFlow is model-agnostic, compatible with all Flow Matching frameworks, and improves generation quality across datasets. Experiments on CIFAR-10, CelebA-64, and ImageNet-256 show that ReflexFlow outperforms prior approaches in mitigating exposure bias, achieving a 35.65% reduction in FID on CelebA-64.
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。