DOS: Diverse Outlier Sampling for Out-of-Distribution Detection

arXiv:2306.02031v2 Announce Type: replace
Abstract: Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outlier dataset to regularize the model during training, and recent studies emphasize the role of uncertainty in designing the sampling strategy for outlier dataset. However, the OOD samples selected solely based on predictive uncertainty can be biased towards certain types, which may fail to capture the full outlier distribution. …

abstract arxiv cs.lg dataset designing detection distribution diverse inputs modern networks neural networks outlier practice prediction role sampling strategy studies training type uncertainty world