通过熵操控缓解基于流的分布外检测中的可能性悖论
Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective
AI总结：
本文通过熵操控缓解基于流的分布外检测中的可能性悖论，利用语义相似性调整输入熵以提高检测性能。
摘要：
能够 tractably 计算输入可能性的深度生成模型，包括归一化流，往往会对分布外（OOD）输入分配出意料之高的可能性。我们通过基于语义相似性的输入熵操控来缓解这种可能性悖论，对与分布内记忆库不相似的输入施加更强的扰动。我们提供了一个理论分析，显示熵控制会增加分布内和OOD样本之间的对数似然差距，有利于分布内样本，并解释了该过程无需对密度模型进行额外训练即可生效。随后，我们在标准基准上评估了我们的方法，并发现相对于基于可能性的OOD检测器，我们的方法在AUROC上一致优于基线，支持我们的解释。
英文摘要：
Deep generative models that can tractably compute input likelihoods, including normalizing flows, often assign unexpectedly high likelihoods to out-of-distribution (OOD) inputs. We mitigate this paradox from an entropic perspective with Semantic Proportional Entropy Manipulation (SPEM), a training-free procedure that applies stronger perturbations to inputs less similar to an in-distribution (ID) memory bank. We derive theoretical lower bounds showing that this entropy gap increases the expected log-likelihood difference in favor of the ID, and experiments on standard benchmarks show that this manipulation realigns the likelihood ordering with human intuition. Strikingly, this realignment persists even when the flow is given only visually meaningless noise instead of the original input, and we analyze this phenomenon theoretically to characterize the conditions under which it occurs.
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。
