论文标题
MMF：开放式识别中功能学习的损失扩展
MMF: A loss extension for feature learning in open set recognition
论文作者
论文摘要
开放式识别（OSR）是对已知类别进行分类的问题，同时识别未知类时，当收集的样品无法用尽所有类时。 OSR问题有许多应用程序。例如，经常出现的新恶意软件类需要一个可以对已知类别进行分类并标识未知的恶意软件类的系统。在本文中，我们建议在神经网络中损失功能的附加扩展，以解决OSR问题。我们的损失扩展利用神经网络找到已知类别的极性表示，以使已知和未知类别的表示形式更有效地可分开。我们的贡献包括：首先，我们引入了一个扩展名，可以将其纳入不同的损失函数以找到更多的歧视性表示。其次，我们表明所提出的扩展可以显着改善来自两个不同域中数据集上两种不同类型的损失函数的性能。第三，我们表明，随着拟议的扩展，一个损失功能在训练时间和模型准确性方面优于其他功能。
Open set recognition (OSR) is the problem of classifying the known classes, meanwhile identifying the unknown classes when the collected samples cannot exhaust all the classes. There are many applications for the OSR problem. For instance, the frequently emerged new malware classes require a system that can classify the known classes and identify the unknown malware classes. In this paper, we propose an add-on extension for loss functions in neural networks to address the OSR problem. Our loss extension leverages the neural network to find polar representations for the known classes so that the representations of the known and the unknown classes become more effectively separable. Our contributions include: First, we introduce an extension that can be incorporated into different loss functions to find more discriminative representations. Second, we show that the proposed extension can significantly improve the performances of two different types of loss functions on datasets from two different domains. Third, we show that with the proposed extension, one loss function outperforms the others in terms of training time and model accuracy.
