GICDM: 缓解枢纽性以实现可靠的基于距离的生成模型评估
GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation
AI总结：
针对生成模型评估中高维嵌入空间的枢纽性现象，提出GICDM方法（基于迭代上下文不相似度度量），通过多尺度扩展校正邻域估计，恢复可靠度量并与人类评估对齐。
摘要：
生成模型评估通常依赖于高维嵌入空间来计算样本之间的距离。我们表明，这些空间中的数据集表示受到枢纽性现象的影响，这会扭曲最近邻关系并使基于距离的度量产生偏差。基于经典的迭代上下文不相似度度量（ICDM），我们引入了生成式ICDM（GICDM），一种校正真实数据和生成数据邻域估计的方法。我们引入了多尺度扩展以改善经验行为。在合成和真实基准上的大量实验表明，GICDM解决了枢纽性引起的失败，恢复了可靠的度量行为，并改善了与人类评估的一致性。
英文摘要：
Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset representations in these spaces are affected by the hubness phenomenon, which distorts nearest-neighbor relationships and biases distance-based metrics. Building on the classical Iterative Contextual Dissimilarity Measure (ICDM), we introduce Generative ICDM (GICDM), a method to correct neighborhood estimation for both real and generated data. We introduce a multi-scale extension to improve empirical behavior. Extensive experiments on synthetic and real benchmarks demonstrate that GICDM resolves hubness-induced failures, restores reliable metric behavior, and improves alignment with human assessment.
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。
