Feature Space Singularity for Out-of-Distribution Detection

30 Nov 2020  ·  Haiwen Huang, Zhihan Li, Lulu Wang, Sishuo Chen, Bin Dong, Xinyu Zhou ·

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}.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Out-of-Distribution Detection CIFAR-10 ResNet 34 + FSSD AUROC 99.5 # 4
Out-of-Distribution Detection Fashion-MNIST LeNet + FSSD AUROC 0.996 # 2
Out-of-Distribution Detection ImageNet dogs vs ImageNet non-dogs ResNet34 + FSSD AUROC 93.1 # 1
Out-of-Distribution Detection MS-1M vs. IJB-C ResNeXt50 + FSSD AUROC 86.7 # 1

Methods


No methods listed for this paper. Add relevant methods here