arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1612.01397cs.LG
收藏

内隐建模--判别式和生成式方法的推广

Implicit Modeling -- A Generalization of Discriminative and Generative Approaches

Dresden University of Technology(德累斯顿工业大学)

Dmitrij Schlesinger, Carsten Rother

摘要:

我们提出了一种新的建模方法,是一个泛化的生成和歧视性模型。其核心思想是通过仅指定条件分布来使用联合概率分布的隐式参数化。所提出的方案结合了两个世界的优点-它可以使用强大的复杂的判别模型作为其部分,同时具有更好的泛化能力。我们彻底评估所提出的方法,一个简单的分类任务与人工数据,并说明其优势,为真实的场景上的语义图像分割问题。

英文摘要:

We propose a new modeling approach that is a generalization of generative and discriminative models. The core idea is to use an implicit parameterization of a joint probability distribution by specifying only the conditional distributions. The proposed scheme combines the advantages of both worlds -- it can use powerful complex discriminative models as its parts, having at the same time better generalization capabilities. We thoroughly evaluate the proposed method for a simple classification task with artificial data and illustrate its advantages for real-word scenarios on a semantic image segmentation problem.

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。

↑