One-Class Convolutional Neural Network
One-Class Convolutional Neural Network
复制标题
一类卷积神经网络
DOI：
10.1109/lsp.2018.2889273
复制
发表时间：
2019-02-01
影响因子：
3.9
通讯作者：
Patel, Vishal M.
中科院分区：
文献类型：
--
作者：
Oza, Poojan;Patel, Vishal M.
提出了一种基于卷积神经网络（CNN）的单类分类方法。其思想是在潜在空间中使用零中心高斯噪声作为伪负类，并使用交叉熵损失来训练网络，以学习给定类的良好表示和决策边界。该方法的一个关键特征是任何预训练的CNN都可以作为单类分类的基础网络。在UMDAA-02 Face、abnormal -1001和FounderType-200数据集上对所提出的一类CNN进行了评估。这些数据集与各种单一类应用问题相关，例如用户身份验证、异常检测和新颖性检测。大量的实验表明，所提出的方法比目前最先进的方法有了显著的改进。源代码可从github.com/otkupjnoz/oc-cnn获得。
We present a novel convolutional neural network (CNN) based approach for one-class classification. The idea is to use a zero centered Gaussian noise in the latent space as the pseudo-negative class and train the network using the cross-entropy loss to learn a good representation as well as the decision boundary for the given class. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one-class classification. The proposed one-class CNN is evaluated on the UMDAA-02 Face, Abnormality-1001, and FounderType-200 datasets. These datasets are related to a variety of one-class application problems such as user authentication, abnormality detection, and novelty detection. Extensive experiments demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. The source code is available at: github.com/otkupjnoz/oc-cnn.