On Outlier Exposure with Generative ModelsDownload PDF

Published: 05 Dec 2022, Last Modified: 05 May 2023MLSW2022Readers: Everyone
Abstract: While Outlier Exposure reliably increases the performance of Out-of-Distribution detectors, it requires a set of available outliers during training. In this paper, we propose Generative Outlier Exposure (GOE), which alleviates the need for available outliers by using generative models to sample synthetic outliers from low-density regions of the data distribution. The approach requires no modification of the generator, works on image and text data, and can be used with pre-trained models. We demonstrate the effectiveness of generated outliers on several image and text datasets, including ImageNet.
1 Reply