Discriminative deep belief networks for visual data classification
Discriminative deep belief networks for visual data classification
复制标题
用于视觉数据分类的判别式深度信念网络
DOI：
10.1016/j.patcog.2010.12.012
复制
发表时间：
2011-10-01
影响因子：
8
通讯作者：
Chen, Qingcai
中科院分区：
文献类型：
--
作者：
Liu, Yan;Zhou, Shusen;Chen, Qingcai
使用不充分的标记数据进行视觉数据分类是一个众所周知的难题。半监督学习是一种尝试利用已有标记数据和未标记数据的学习方法，近年来引起了广泛的关注。本文提出了一种新的半监督分类器，称为判别式深度信念网络（DDBN）。DDBN利用一种新的深度体系结构，将深度信念网（DBN）的抽象能力和反向传播策略的区分能力结合起来。对于无监督学习，DDBN继承了DBN的优点，从高维特征空间到低维嵌入都能很好地保留信息。对于监督学习，通过设计良好的目标函数，反向传播策略通过细化参数空间直接优化训练数据集中的分类结果。此外，我们将DDBN应用于视觉数据分类任务，并观察到一个重要的事实，即深度架构的学习能力在现实世界的应用中被严重低估，特别是在视觉数据分析中。在不同类型和不同尺度的标准数据集上的对比实验表明，该算法的性能优于典型的半监督分类器和现有的深度学习技术。对于可视化数据集，我们可以进一步提高DDBN的性能更大和更深的架构。(C)2010爱思唯尔有限公司版权所有。
Visual data classification using insufficient labeled data is a well-known hard problem. Semi-supervise learning, which attempts to exploit the unlabeled data in additional to the labeled ones, has attracted much attention in recent years. This paper proposes a novel semi-supervised classifier called discriminative deep belief networks (DDBN). DDBN utilizes a new deep architecture to integrate the abstraction ability of deep belief nets (DBN) and discriminative ability of backpropagation strategy. For unsupervised learning, DDBN inherits the advantage of DBN, which preserves the information well from high-dimensional features space to low-dimensional embedding. For supervised learning, through a well designed objective function, the backpropagation strategy directly optimizes the classification results in training dataset by refining the parameter space. Moreover, we apply DDBN to visual data classification task and observe an important fact that the learning ability of deep architecture is seriously underrated in real-world applications, especially in visual data analysis. The comparative experiments on standard datasets of different types and different scales demonstrate that the proposed algorithm outperforms both representative semi-supervised classifiers and existing deep learning techniques. For visual dataset, we can further improve the DDBN performance with much larger and deeper architecture. (C) 2010 Elsevier Ltd. All rights reserved.