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 1109.4389stat.ML
收藏

应用于多尺度图像表示的条件高斯尺度混合

Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations

Lucas Theis, Reshad Hosseini, Matthias Bethge

摘要:

我们提出了一个自然图像的概率模型,它是基于高斯尺度混合和一个简单的多尺度表示。在对比的主导方法来建模整个图像集中在马尔可夫随机场,我们制定我们的模型在一个有向图形模型。我们表明,它是能够生成有趣的高阶相关性的图像时,自然图像或样本从基于遮挡的模型进行训练。更重要的是,有向模型使我们能够进行原则性的评估。虽然它很容易生成视觉上吸引人的图像,我们证明,我们的模型也产生了最好的性能报告的日期时,评估相对于交叉熵率,一个措施紧密联系在一起的平均对数似然。

英文摘要:

We present a probabilistic model for natural images which is based on Gaussian scale mixtures and a simple multiscale representation. In contrast to the dominant approach to modeling whole images focusing on Markov random fields, we formulate our model in terms of a directed graphical model. We show that it is able to generate images with interesting higher-order correlations when trained on natural images or samples from an occlusion based model. More importantly, the directed model enables us to perform a principled evaluation. While it is easy to generate visually appealing images, we demonstrate that our model also yields the best performance reported to date when evaluated with respect to the cross-entropy rate, a measure tightly linked to the average log-likelihood.

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。

↑