Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks

Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks
复制标题

DOI：
10.1007/978-3-030-86520-7_1
复制
发表时间：
2021-06
期刊：
ArXiv
影响因子：
--
通讯作者：
Jun Zhuang;M. Hasan
Jun Zhuang;M. Hasan
中科院分区：
其他
文献类型：
--
作者：
Jun Zhuang;M. Hasan

文献摘要

相似文献

监督学习虽然部署在现实生活中，但经常遇到未知类的实例。用于训练监督学习模型的传统算法不提供检测此类实例的选项，因此它们以100%的概率对此类实例进行误分类。开集识别（OSR）和非穷举学习（NEL）是克服这个问题的潜在解决方案。大多数现有的OSR方法首先对现有类的成员进行分类，然后识别新类的实例。然而，许多现有的OSR方法只进行二元决策，即，它们只识别未知类的存在。因此，这样的方法不能区分属于增量不可见类的测试实例。另一方面，大多数NEL方法通常对数据分布进行参数假设，由于现实生活中复杂的数据集可能不遵循众所周知的数据分布，因此无法返回良好的结果。在本文中，我们提出了一种新的在线非穷举学习模型，即非穷举高斯混合生成对抗网络（NE-GM-GAN）来解决这些问题。我们提出的模型在深度生成模型（如GAN）上合成了基于高斯混合的潜在表示，用于增量检测测试数据中新兴类的实例。在多个基准数据集上的大量实验结果表明，NE-GM-GAN在检测流数据中新类的实例方面明显优于现有的方法。
Supervised learning, while deployed in real-life scenarios, often encounters instances of unknown classes. Conventional algorithms for training a supervised learning model do not provide an option to detect such instances, so they miss-classify such instances with 100% probability. Open Set Recognition (OSR) and Non-Exhaustive Learning (NEL) are potential solutions to overcome this problem. Most existing methods of OSR first classify members of existing classes and then identify instances of new classes. However, many of the existing methods of OSR only makes a binary decision, i.e., they only identify the existence of the unknown class. Hence, such methods cannot distinguish test instances belonging to incremental unseen classes. On the other hand, the majority of NEL methods often make a parametric assumption over the data distribution, which either fail to return good results, due to the reason that real-life complex datasets may not follow a well-known data distribution. In this paper, we propose a new online non-exhaustive learning model, namely, Non-Exhaustive Gaussian Mixture Generative Adversarial Networks (NE-GM-GAN) to address these issues. Our proposed model synthesizes Gaussian mixture based latent representation over a deep generative model, such as GAN, for incremental detection of instances of emerging classes in the test data. Extensive experimental results on several benchmark datasets show that NE-GM-GAN significantly outperforms the state-of-the-art methods in detecting instances of novel classes in streaming data.