Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment
arXiv:2011.13120
Abstract
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.
arXiv commentAccepted to NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice
References in corpus (9)
- Auto-Encoding Variational Bayes
- mixup: Beyond Empirical Risk Minimization
- Language Models are Few-Shot Learners
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Deep Anomaly Detection with Outlier Exposure
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
- Natural Adversarial Examples
- Contrastive Training for Improved Out-of-Distribution Detection
- Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks