A Method Based on Convex Cone Model for Image-Set Classification With CNN Features
A Method Based on Convex Cone Model for Image-Set Classification With CNN Features
复制标题
DOI：
10.1109/ijcnn.2018.8489151
复制
发表时间：
2018-05
期刊：
影响因子：
--
通讯作者：
Naoya Sogi;Taku Nakayama;K. Fukui
中科院分区：
文献类型：
--
作者：
Naoya Sogi;Taku Nakayama;K. Fukui
在本文中，我们提出了一种基于凸锥模型的图像集分类方法，重点关注卷积神经网络（CNN）特征作为输入的有效性。当使用整流线性单元作为激活函数时，CNN特征是非负值。这自然导致我们通过凸锥对一组CNN特征进行建模，并测量凸锥在分类中的几何相似性。为了实现这个框架，我们通过重复交替最小二乘法来定义两个凸锥之间的顺序多角度，然后使用得到的角度来定义凸锥之间的几何相似性。此外，为了增强我们的方法，我们引入了一个判别空间，它使投影凸锥在判别空间上的类间方差（间隙）最大化，类内方差最小化，类似于Fisher判别分析。最后，通过测量投影凸锥之间的相似度进行分类。在一个多视图手形数据集的私有数据库和两个公共数据库上进行了评估实验，验证了该方法的有效性。
In this paper, we propose a method for image-set classification based on convex cone models, focusing on the effectiveness of convolutional neural network (CNN) features as its input. CNN feature has non-negative values when using the rectified linear unit as an activation function. This naturally leads us to model a set of CNN features by a convex cone and measure the geometrical similarity of convex cones in classification. To achieve this framework, we define sequentially multiple angles between two convex cones by repeating the alternating least square method, and then define the geometrical similarity between the cones by using the obtained angles. Moreover, to enhance our method, we introduce a discriminant space, which maximizes the between-class variance (gaps) and minimizes the within-class variance of the projected convex cones onto the discriminant space, like Fisher discriminant analysis. Finally, the classification is conducted by measuring the similarity between projected convex cones. The effectiveness of the proposed method is demonstrated through evaluation experiments on a private database of a multi-view hand shape dataset, and two public databases.