arXiv cs.AI· Tadeusz Dziarmaga, Marcin K\k{a}dzio{\l}ka, Laura Musio{\l}, Patryk Marsza{\l}ek, Artur Kasymov, Piotr Ko\'scielniak, Marcin Mazur·· 12 小时前AI 评分24
PALATE：用全期望定律改进深度生成模型评估的新框架
PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models
AI 导读
PALATE 框架通过将全期望定律应用于可访问数据的随机变量，解决了 Feature Likelihood Divergence（FLD）的计算效率瓶颈。结合 MMD 基线指标与 DINOv3 特征提取器后，PALATE 在匹配或超越 SOTA 方法的同时具备更优的计算效率与大规模数据集扩展性。实验显示其在检测样本记忆和评估泛化能力方面表现实用，源代码已作为补充材料提供。
正文 · 原文
Abstract:Deep generative models (DGMs) have caused a paradigm shift in the field of machine learning, yielding noteworthy advancements in domains such as image synthesis, natural language processing, and other related areas. However, a comprehensive evaluation of these models that effectively captures the interplay among fidelity, diversity, and novelty in generated samples remains a persistent challenge. A recently proposed approach, the Feature Likelihood Divergence (FLD), offers a theoretically grounded and practical tool in this regard but faces notable computational limitations. In this paper, we propose PALATE, a novel framework designed to enhance the evaluation of DGMs by addressing the efficiency constraints of FLD. Our approach is based on a peculiar application of the law of total expectation to random variables representing accessible data. When integrated with the MMD baseline metric and the recently introduced DINOv3 feature extractor, PALATE provides a comprehensive evaluation framework that matches or exceeds state-of-the-art methods while offering superior computational efficiency and scalability to large-scale datasets. Through a series of experiments, we demonstrate that the PALATE enhancement constitutes a practical and computationally efficient framework for holistic DGM assessment, particularly in detecting sample memorization and evaluating generalization capabilities. The source code is provided as supplementary material.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2503.18462 [cs.LG] |
| (or arXiv:2503.18462v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2503.18462 arXiv-issued DOI via DataCite |
Submission history
From: Tadeusz Dziarmaga [view email]
[v1]
Mon, 24 Mar 2025 09:06:45 UTC (638 KB)
[v2]
Mon, 19 Oct 2026 23:41:32 UTC (5,998 KB)
来源：arXiv cs.AI · arxiv.org