论文标题
特征空间奇异性用于分布外检测
Feature Space Singularity for Out-of-Distribution Detection
论文作者
论文摘要
分布（OOD）检测对于建立安全的人工智能系统很重要。但是，当前的OOD检测方法仍然无法满足实际部署的性能要求。在本文中，我们提出了一种基于新颖的观察结果的简单而有效的算法：在训练有素的神经网络中，具有有界规范的OOD样品在特征空间中良好。我们将OOD中心称为特征空间奇点（FSS），并表示样品特征与FSS的距离为FSSD。然后，可以通过在FSSD上阈值来识别OOD样品。我们对现象的分析揭示了为什么我们的算法起作用。我们证明，我们的算法在各种OOD检测基准上实现了最先进的性能。此外，FSSD在测试数据中还具有鲁棒性，可以通过结合进一步增强。这些使FSSD成为现实世界中有望使用的算法。我们以\ url {https://github.com/megvii-research/fssd_ood_detection}发布代码。
Out-of-Distribution (OoD) detection is important for building safe artificial intelligence systems. However, current OoD detection methods still cannot meet the performance requirements for practical deployment. In this paper, we propose a simple yet effective algorithm based on a novel observation: in a trained neural network, OoD samples with bounded norms well concentrate in the feature space. We call the center of OoD features the Feature Space Singularity (FSS), and denote the distance of a sample feature to FSS as FSSD. Then, OoD samples can be identified by taking a threshold on the FSSD. Our analysis of the phenomenon reveals why our algorithm works. We demonstrate that our algorithm achieves state-of-the-art performance on various OoD detection benchmarks. Besides, FSSD also enjoys robustness to slight corruption in test data and can be further enhanced by ensembling. These make FSSD a promising algorithm to be employed in real world. We release our code at \url{https://github.com/megvii-research/FSSD_OoD_Detection}.
