Test-Time Learning for Outlier Detection

In this work, the concept of test-time learning is presented, wherein Machine-Learning (ML) models are constructed by involving unlabeled test samples. Based on this concept, we propose a method called Local Augment (LA) designed to improve the performance of trained outlier detectors at the prediction stage without altering the trained models or accessing the training data. LA operates under the only assumption that the model should produce similar outputs for similar inputs, implying that the prediction of a given sample can be enhanced by the predictions for its similar samples. Specifically, LA boosts outlier detection performance during prediction by fusing the outlier score of a given sample with the scores of synthetically neighboring samples generated by adding random perturbations to the given sample. This simple method demonstrates an average improvement of about +0.04 Area Under the Receiver Operating Characteristic curve (AUROC) across 26 real-world datasets for all 14 tested detectors. Notably, this represents the pioneering work of enhancing ML models during the prediction stage without the need to modify the trained models or access the training dataset. This work opens up new possibilities for addressing existing bottleneck problems in various ML tasks beyond outlier detection in diverse domains.