Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment
This work provides a more controlled evaluation for researchers developing OOD detection methods, particularly those leveraging self-supervised learning.
This paper evaluates the out-of-distribution (OOD) detection performance of self-supervised learning (SSL) techniques using a new framework that controls the distance of OOD samples from in-distribution samples. SSL methods consistently showed improved OOD detection performance across simulated samples, images, and text.
We evaluate the out-of-distribution (OOD) detection performance of self-supervised learning (SSL) techniques with a new evaluation framework. Unlike the previous evaluation methods, the proposed framework adjusts the distance of OOD samples from the in-distribution samples. We evaluate an extensive combination of OOD detection algorithms on three different implementations of the proposed framework using simulated samples, images, and text. SSL methods consistently demonstrated the improved OOD detection performance in all evaluation settings.