A Median Perspective on Unlabeled Data for Out-of-Distribution Detection
This work addresses the problem of improving robustness in machine learning systems for real-world applications, though it appears incremental as it builds on prior use of unlabeled data for OOD detection.
The paper tackled the challenge of out-of-distribution detection using unlabeled data by introducing Medix, a framework that identifies outliers via median operations and trains a robust classifier, achieving low error rates and outperforming existing methods in open-world settings.
Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness and reliability of machine learning systems deployed in real-world applications. Recent approaches have explored the use of unlabeled data, showing potential for enhancing OOD detection capabilities. However, effectively utilizing unlabeled in-the-wild data remains challenging due to the mixed nature of both in-distribution (InD) and OOD samples. The lack of a distinct set of OOD samples complicates the task of training an optimal OOD classifier. In this work, we introduce Medix, a novel framework designed to identify potential outliers from unlabeled data using the median operation. We use the median because it provides a stable estimate of the central tendency, as an OOD detection mechanism, due to its robustness against noise and outliers. Using these identified outliers, along with labeled InD data, we train a robust OOD classifier. From a theoretical perspective, we derive error bounds that demonstrate Medix achieves a low error rate. Empirical results further substantiate our claims, as Medix outperforms existing methods across the board in open-world settings, confirming the validity of our theoretical insights.