A semi-supervised convolutional neural network based on subspace representation for image classification
A semi-supervised convolutional neural network based on subspace representation for image classification
复制标题
基于子空间表示的半监督卷积神经网络用于图像分类
DOI：
10.1186/s13640-020-00507-5
复制
发表时间：
2020-06-16
影响因子：
2.4
通讯作者：
dos Santos, Kenny V.
中科院分区：
文献类型：
--
作者：
Gatto, Bernardo B.;Souza, Lincon S.;dos Santos, Kenny V.
本文提出了一种基于子空间的浅网络，并将其应用于图像分类。近年来，基于PCA滤波器组的浅层网络已被用于解决许多与计算机视觉相关的问题，包括纹理分类、人脸识别和场景理解。这些方法是健壮的，具有一个简单的实现，可以实现实际应用程序的快速原型。然而，这些体系结构要么采用无监督学习，要么采用监督学习。因此，由于每种学习范式的缺陷，它们可能无法在更复杂的计算机视觉问题中实现高度判别特征，这些问题包含相机运动、物体外观、姿态、规模和纹理的变化。为了克服这一缺点，我们提出了一种半监督浅网络，同时配备了无监督和有监督滤波器组，具有代表性和判别能力。此外，所引入的体系结构灵活，在不同的应用程序中表现良好，这些应用程序的监督数据量是一个问题，使其在实践中成为一个有吸引力的选择。该网络在五个数据集上进行了评估。结果表明，与现有浅层网络相比，该方法在预测率方面有所提高。
This work presents a shallow network based on subspaces with applications in image classification. Recently, shallow networks based on PCA filter banks have been employed to solve many computer vision-related problems including texture classification, face recognition, and scene understanding. These approaches are robust, with a straightforward implementation that enables fast prototyping of practical applications. However, these architectures employ either unsupervised or supervised learning. As a result, they may not achieve highly discriminative features in more complicated computer vision problems containing variations in camera motion, object's appearance, pose, scale, and texture, due to drawbacks related to each learning paradigm. To cope with this disadvantage, we propose a semi-supervised shallow network equipped with both unsupervised and supervised filter banks, presenting representative and discriminative abilities. Besides, the introduced architecture is flexible, performing favorably on different applications whose amount of supervised data is an issue, making it an attractive choice in practice. The proposed network is evaluated on five datasets. The results show improvement in terms of prediction rate, comparing to current shallow networks.