用反向外推修复自训练导致的图像生成退化，提升模型质量。
Neon: Negative Extrapolation From Self-Training Improves Image Generation
- 通过反向梯度外推，将自训练退化的权重恢复到真实数据分布附近。
- 仅用1000张合成数据，额外计算量不足1%，在ImageNet上实现FID 1.02新纪录。
- 通用性强，适用于扩散、流匹配等多类模型和数据集，无需新真实数据。
生成式AI模型的扩展受限于高质量训练数据的稀缺性。利用生成模型合成数据以扩充真实数据，虽可缓解数据不足，但易引发模型自噬症（MAD），导致样本质量与多样性快速下降。本文提出Neon（负外推自训练），一种新学习方法，将自训练退化转化为自我改进信号。给定基础模型后，Neon先用其自合成数据微调，再反向梯度更新，外推远离退化权重。理论证明，典型采样器倾向于高概率区域，使合成与真实数据梯度呈现可预测的反对齐，负外推可纠正此偏差，使模型更贴近真实数据分布。Neon可通过简单后处理合并实现，无需新真实数据，仅需约1000张合成样本，额外训练计算量低于1%。在扩散、流匹配、自回归及归纳矩匹配模型上均有效，覆盖ImageNet、CIFAR-10、FFHQ等数据集。尤其在ImageNet 256x256上，将xAR-L模型提升至新最佳FID 1.02，仅增加0.36%训练计算量。代码已开源。
原文摘要 · Abstract (English)
Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic data to augment a limited corpus of real data for the purpose of fine-tuning in the hope of improving performance. Unfortunately, however, the resulting positive feedback loop leads to model autophagy disorder (MAD, aka model collapse) that results in a rapid degradation in sample quality and/or diversity. In this paper, we introduce Neon (for Negative Extrapolation frOm self-traiNing), a new learning method that turns the degradation from self-training into a powerful signal for self-improvement. Given a base model, Neon first fine-tunes it on its own self-synthesized data but then, counterintuitively, reverses its gradient updates to extrapolate away from the degraded weights. We prove that Neon works because typical inference samplers that favor high-probability regions create a predictable anti-alignment between the synthetic and real data population gradients, which negative extrapolation corrects to better align the model with the true data distribution. Neon is remarkably easy to implement via a simple post-hoc merge that requires no new real data, works effectively with as few as 1k synthetic samples, and typically uses less than 1% additional training compute. We demonstrate Neon's universality across a range of architectures (diffusion, flow matching, autoregressive, and inductive moment matching models) and datasets (ImageNet, CIFAR-10, and FFHQ). In particular, on ImageNet 256x256, Neon elevates the xAR-L model to a new state-of-the-art FID of 1.02 with only 0.36% additional training compute. Code is available at https://github.com/VITA-Group/Neon
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。