Real-world machine learning systems need to analyze novel testing data that differs from the training data. In K-way classification, this is crisply formulated as open-set recognition, core to which is the ability to discriminate open-set data outside the K closed-set classes. Two conceptually elegant ideas for open-set discrimination are: 1) discriminatively learning an open-vs-closed binary discriminator by exploiting some outlier data as the open-set, and 2) unsupervised learning the closed-set data distribution with a GAN and using its discriminator as the open-set likelihood function. However, the former generalizes poorly to diverse open test data due to overfitting to the training outliers, which unlikely exhaustively span the open-world. The latter does not work well, presumably due to the instable training of GANs. Motivated by the above, we propose OpenGAN, which addresses the limitation of each approach by combining them with several technical insights. First, we show that a carefully selected GAN-discriminator on some real outlier data already achieves the state-of-the-art. Second, we augment the available set of real open training examples with adversarially synthesized "fake" data. Third and most importantly, we build the discriminator over the features computed by the closed-world K-way networks. Extensive experiments show that OpenGAN significantly outperforms prior open-set methods.

翻译：现实世界机器学习系统需要分析与培训数据不同的新测试数据。 在 Kway 分类中, 这是以开放的识别方式, 直截了当地设计成开放的测试数据, 其核心是能够在 K 封闭型类之外对开放型数据进行歧视。 开放型歧视的两个概念优雅的理念是:(1) 以开放型方式利用一些外部数据作为开放型数据, 从而有区别地学习开放型数据, 2) 不受监督地学习与 GAN 一起的封闭型数据分布, 并使用其导师作为开放型的可能性函数。 但是, 前者由于过度适应培训型外端数据, 核心是无法做到多种开放型的公开测试数据。 后者可能由于对 GAN 的不固定型培训, 我们提出OpenGAN, 通过将每种方法的局限性与若干技术见解结合起来来加以解决。 首先, 我们展示了一个精心选择的 GAN - 差异型分化型数据, 已经实现了开放型的状态- 开放型的模拟网络 。 第二, 我们通过我们展示了我们所具备的初始型的G- tral- tral- greal- greal- greal vial viewd exal exal ex ex viewd dreal view vial vial viewd viewd viewd viewd viewd viewd viewd viewd viewdal viewd viewd data view viewd data viewd viewd viewd dd dd data viewd viewd viewd viewd viewd viewd viewd viewd viewd vial commal comm viewd comm comm comm comm viewd viewd viewd dal vial ex ex viewd dal comm