Unsupervised Unknown Unknown Detection in Active Learning

Unknown unknowns in machine learning signify data points outside the distribution of known data and constitute blindspots of traditional machine learning models. As these data points typically involve rare and unexpected scenarios, the models may make wrong predictions, potentially leading to catastrophic situations. Detecting "unknown unknowns" is essential to ensure machine learning systems' reliability and robustness and avoid unexpected failures in real-world safety-critical applications. This paper proposes an Unsupervised Unknown Unknown Detection in Active Learning (U3DAL) to detect "unknown unknowns" in a stream-based data setting using active learning data selection mechanisms that rely on uncertainty and diversity. The effectiveness of the proposed approach is validated on the Imagenet-A dataset and across different metrics, demonstrating that it outperforms existing methods for detecting "unknown unknowns".