DCR：反事实吸引引导用于稀有组合生成
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
AI总结：
本文提出DCR框架，通过反事实吸引引导解决扩散模型在生成稀有但合理的组合时的默认完成偏见问题，提升生成内容的组合忠实度和视觉质量。
摘要：
扩散模型能生成逼真视觉内容，但常难以生成稀有但合理的组合。当提示包含训练数据中较少见但有效的组合，如雪地海滩或夜晚彩虹时，生成过程常倾向于更常见的替代。本文将这种失败模式称为默认完成偏见，即去噪轨迹隐式吸引向高频语义配置。现有引导机制未显式建模此竞争倾向，难以防止此类崩溃。本文引入默认完成排斥（DCR），一种无需训练的框架，显式建模并抑制默认完成行为。DCR通过放松稀有组合因素同时保持周围语义，构建反事实吸引子，诱导替代去噪轨迹反映模型偏好完成。定义目标与吸引子轨迹之间的差异为反事实漂移，并提出基于投影的排斥机制，移除与漂移方向一致的引导组件。这抑制了不希望的频繁完成，同时保持其他语义组件。DCR完全在标准扩散采样过程中运行，无需重训练或架构修改。实验表明，DCR在稀有组合提示上提升组合忠实度并保持视觉质量。进一步分析显示，该框架暴露并对抗内在模型偏见，提供了一种新的可控生成视角，超越显式约束强制。
英文摘要：
Diffusion models generate realistic visual content, yet often fail to produce rare but plausible compositions. When prompted with combinations that are valid but underrepresented in training data, such as a snowy beach or a rainbow at night, the generation process frequently collapses toward more common alternatives. We identify this failure mode as default completion bias, where denoising trajectories are implicitly attracted toward high-frequency semantic configurations. Existing guidance mechanisms do not explicitly model this competing tendency and therefore struggle to prevent such collapse. We introduce Default Completion Repulsion (DCR), a training-free framework that explicitly models and suppresses default completion behavior. DCR constructs a counterfactual attractor by relaxing the rare compositional factor while preserving surrounding semantics, inducing an alternative denoising trajectory reflecting the model's preferred completion. We define the discrepancy between target and attractor trajectories as a counterfactual drift, and propose a projection-based repulsion mechanism that removes guidance components aligned with this drift direction. This suppresses undesired frequent completions while preserving other semantic components. DCR operates entirely within the standard diffusion sampling process without retraining or architectural modification. Experiments on rare compositional prompts show that DCR improves compositional fidelity while maintaining visual quality. Our analysis further shows that the framework exposes and counteracts intrinsic model biases, offering a new perspective on controllable generation beyond explicit constraint enforcement.
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。
