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

TL;DR

This paper introduces DOS, a novel outlier sampling method that emphasizes diversity to improve out-of-distribution detection in neural networks, outperforming existing approaches by effectively capturing the full outlier distribution.

Contribution

The paper proposes a simple yet effective clustering-based sampling strategy called DOS that enhances OOD detection by ensuring diverse outlier selection.

Findings

DOS reduces FPR95 by up to 25.79% on CIFAR-100 with TI-300K.

Diversity in outlier sampling improves the decision boundary between ID and OOD data.

Sampling from diverse clusters leads to better OOD detection performance.

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. In this work, we empirically show that diversity is critical in sampling outliers for OOD detection performance. Motivated by the observation, we propose a straightforward and novel sampling strategy named DOS (Diverse Outlier Sampling) to select diverse and informative outliers. Specifically, we cluster the normalized features at each iteration, and the most informative outlier from each cluster is selected for model training with absent category loss. With DOS, the sampled outliers efficiently shape a globally compact decision boundary between ID and OOD data. Extensive experiments demonstrate the superiority of DOS, reducing the average FPR95 by up to 25.79% on CIFAR-100 with TI-300K.