用条件概率建模多变量分布，支持任意下游任务。
Deep Multivariate Models with Parametric Conditionals
- 以每组变量对其他变量的条件分布构建联合模型
- 通过最大化数据似然训练，可实现半监督学习
- 适合需要灵活推理的视觉多模态任务
我们研究用于异构随机变量集合的深度多变量模型。在计算机视觉中，这类集合可能包括图像、分割图、图像属性和隐变量等。现有方法通常从具体任务出发设计模型结构与依赖关系，限制了模型在其他下游任务中的适用性。本文提出通过每个变量组对其余变量的条件概率分布来表示联合概率分布，从而支持几乎所有下游任务。模型可通过最大化其极限分布的数据似然来训练，相当于训练一个参数化的马尔可夫链核，同时具备广泛的半监督学习能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。