arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.08785cs.LG
收藏

基于能量模型的分布外检测

On Out-of-distribution Detection with Energy-based Models

Technical University Munich(慕尼黑工业大学)

Sven Elflein, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann

摘要:

几种密度估计方法已被证明无法通过将更高的可能性分配给异常数据来检测分布外(OOD)样本。基于能量的模型(EBM)是灵活的,非规范化的密度模型,似乎能够改善这种故障模式。在这项工作中,我们提供了一个广泛的研究调查OOD检测与EBM训练与不同的方法对表格和图像数据,并发现EBM不提供一致的优势。我们假设EBM不学习语义特征,尽管它们的歧视性结构类似于规范化流。为了验证这一假设,我们表明,监督和建筑的限制提高了OOD检测EBM独立的训练方法。

英文摘要:

Several density estimation methods have shown to fail to detect out-of-distribution (OOD) samples by assigning higher likelihoods to anomalous data. Energy-based models (EBMs) are flexible, unnormalized density models which seem to be able to improve upon this failure mode. In this work, we provide an extensive study investigating OOD detection with EBMs trained with different approaches on tabular and image data and find that EBMs do not provide consistent advantages. We hypothesize that EBMs do not learn semantic features despite their discriminative structure similar to Normalizing Flows. To verify this hypotheses, we show that supervision and architectural restrictions improve the OOD detection of EBMs independent of the training approach.

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。

↑