EMoE: 面向不确定性感知的文本到图像扩散的无训练专家分歧方法
EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion
AI总结：
提出EMoE方法，通过预训练MoE扩散模型中早期MoE层的专家分歧，无需训练即可估计认知不确定性，用于提示风险诊断和生成质量排序。
摘要：
大型文本到图像扩散模型很少在提示可能产生低质量生成时提供可靠信号，尤其是在训练数据未公开的情况下。我们研究预训练混合专家（MoE）扩散模型中的专家分歧是否可以作为认知不确定性的可靠估计。我们引入EMoE，一种无训练方法，在早期MoE层分离专家特定的计算路径，跨路径使用相同的初始噪声，并在第一步去噪后测量其潜在表示之间的方差。这提供了在完整图像生成之前的不确定性感知提示信号，无需辅助网络或训练扩散集成。在COCO和CC3M上，EMoE根据文本-图像对齐质量指标对提示进行排序，比扩散特定和基于路由的基线更一致。我们进一步将EMoE应用于多语言提示，并发现分歧和生成质量中存在系统的语言依赖性差异，包括共享词汇效应。这些结果使EMoE成为MoE文本到图像扩散模型中提示风险、模型覆盖和偏差分析的实用诊断工具。
英文摘要：
Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially when training data is undisclosed. We study whether expert disagreement inside pre-trained mixture-of-experts (MoE) diffusion models can serve as a reliable estimate for epistemic uncertainty. We introduce EMoE, a training-free method that separates expert-specific computation paths at an early MoE layer, uses the same initial noise across paths, and measures variance among their latent representations after the first denoising step. This provides an uncertainty-aware prompt signal before full image generation, without auxiliary networks or training diffusion ensembles. On COCO and CC3M, EMoE ranks prompts by text-image alignment quality metrics more consistently than diffusion-specific and router-based baselines. We further apply EMoE to multilingual prompts and find systematic language-dependent differences in disagreement and generation quality, including shared-vocabulary effects. These results position EMoE as a practical diagnostic tool for prompt risk, model coverage, and bias analysis in MoE text-to-image diffusion models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
