Feature Space Singularity for Out-of-Distribution Detection
This work aims to improve the reliability and safety of AI systems by enhancing out-of-distribution detection capabilities, which is a critical problem for deploying AI in real-world scenarios.
This paper addresses the problem of out-of-distribution (OoD) detection by observing that OoD samples with bounded norms concentrate in a "Feature Space Singularity" (FSS) within a trained neural network. By measuring the distance to this FSS, their algorithm achieves state-of-the-art performance on various OoD detection benchmarks.
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}.