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 2602.01953cs.LGstat.ML
收藏

具有参数条件的深度多变量模型

Deep Multivariate Models with Parametric Conditionals

Dresden University of Technology(德累斯顿技术大学);Czech Technical University in Prague(布拉格捷克技术大学)

Dmitrij Schlesinger, Boris Flach, Alexander Shekhovtsov

AI总结:

本文提出了一种基于参数条件的深度多变量模型,通过联合概率分布的条件表示提升模型在多种下游任务中的适用性,并利用马尔可夫链核进行学习。

摘要:

我们考虑了用于异质随机变量集合的深度多变量模型。在计算机视觉的背景下,此类集合可能例如由图像、分割图、图像属性和潜在变量组成。在开发此类模型时,大多数现有工作都是从应用任务出发,设计模型组件及其依赖关系以满足所选任务的需求。这有缺点,即限制了所得到模型在其他下游任务中的适用性。在这里,我们提出通过将联合概率分布表示为每个变量组对剩余变量的条件概率分布来表示。此类模型可以用于任何可能的下游任务。其学习可以视为通过最大化其极限分布的数据似然来训练参数化的马尔可夫链核。这还具有允许广泛半监督学习场景的优势。

英文摘要:

We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentations, image attributes, and latent variables. When developing such models, most existing works start from an application task and design the model components and their dependencies to meet the needs of the chosen task. This has the disadvantage of limiting the applicability of the resulting model for other downstream tasks. Here, instead, we propose to represent the joint probability distribution by means of conditional probability distributions for each group of variables conditioned on the rest. Such models can then be used for practically any possible downstream task. Their learning can be approached as training a parametrised Markov chain kernel by maximising the data likelihood of its limiting distribution. This has the additional advantage of allowing a wide range of semi-supervised learning scenarios.

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。

↑