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.
@article{arxiv.2011.13120,
title = {Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment},
author = {Jeonghoon Park and Kyungmin Jo and Daehoon Gwak and Jimin Hong and Jaegul Choo and Edward Choi},
journal= {arXiv preprint arXiv:2011.13120},
year = {2021}
}
Comments
Accepted to NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice