arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.09628cs.CVstat.ML
收藏

用于图像去噪与分类的结构化受限玻尔兹曼机

Structural Restricted Boltzmann Machine for image denoising and classification

Intelligent Systems Group(智能系统组)

Arkaitz Bidaurrazaga, Aritz Pérez, Roberto Santana

AI总结:

针对传统受限玻尔兹曼机参数过多的问题,提出基于图像像素空间邻域约束隐藏单元连接的结构化RBM,在图像去噪和分类任务上实现了更快更稳定的训练和更优性能。

摘要:

受限玻尔兹曼机(Restricted Boltzmann Machines,RBM)是一类生成模型,由一层与可见单元层相连的隐藏变量层构成,用于对可见变量的分布进行建模。为获得更强的表征能力,通常会使用大量隐藏单元,这与数量众多的可见单元相结合,会导致可训练参数的规模极高。在本研究中,我们提出了结构化受限玻尔兹曼机(Structural Restricted Boltzmann Machine)模型,该模型利用手头数据的结构,将隐藏单元的连接限制在可见单元的子集内,以在不损失性能的前提下显著减少可训练参数的数量。作为潜在的应用方向,我们聚焦于图像建模。基于图像的特性,连接结构以图像像素上的空间邻域来定义,这些像素构成了模型的可见变量。我们在多个图像领域开展了大量实验。图像去噪效果使用MNIST数据集中的含噪图像进行评估。我们将所提模型的生成能力与普通RBM(vanilla RBM)进行了对比,同时也对比了二者的分类性能——分类性能在五个不同的图像领域上进行评估。结果表明,与可见单元和隐藏单元之间无连接约束的RBM相比,我们提出的模型训练速度更快、过程更稳定,同时还能取得更优的效果。

英文摘要:

Restricted Boltzmann Machines are generative models that consist of a layer of hidden variables connected to another layer of visible units, and they are used to model the distribution over visible variables. In order to gain a higher representability power, many hidden units are commonly used, which, in combination with a large number of visible units, leads to a high number of trainable parameters. In this work we introduce the Structural Restricted Boltzmann Machine model, which taking advantage of the structure of the data in hand, constrains connections of hidden units to subsets of visible units in order to reduce significantly the number of trainable parameters, without compromising performance. As a possible area of application, we focus on image modelling. Based on the nature of the images, the structure of the connections is given in terms of spatial neighbourhoods over the pixels of the image that constitute the visible variables of the model. We conduct extensive experiments on various image domains. Image denoising is evaluated with corrupted images from the MNIST dataset. The generative power of our models is compared to vanilla RBMs, as well as their classification performance, which is assessed with five different image domains. Results show that our proposed model has a faster and more stable training, while also obtaining better results compared to an RBM with no constrained connections between its visible and hidden units.

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。

↑