Task Agnostic and Post-hoc Unseen Distribution Detection
It addresses a gap in OOD detection, anomaly detection, and uncertainty estimation for machine learning practitioners, but is incremental as it builds on existing clustering and Mahalanobis distance techniques.
The paper tackles the lack of a task-agnostic and post-hoc method for unseen distribution detection by proposing TAPUDD, a clustering-based ensembling approach that uses features from trained models, and shows it performs better or on-par with baselines across diverse tasks.
Despite the recent advances in out-of-distribution(OOD) detection, anomaly detection, and uncertainty estimation tasks, there do not exist a task-agnostic and post-hoc approach. To address this limitation, we design a novel clustering-based ensembling method, called Task Agnostic and Post-hoc Unseen Distribution Detection (TAPUDD) that utilizes the features extracted from the model trained on a specific task. Explicitly, it comprises of TAP-Mahalanobis, which clusters the training datasets' features and determines the minimum Mahalanobis distance of the test sample from all clusters. Further, we propose the Ensembling module that aggregates the computation of iterative TAP-Mahalanobis for a different number of clusters to provide reliable and efficient cluster computation. Through extensive experiments on synthetic and real-world datasets, we observe that our approach can detect unseen samples effectively across diverse tasks and performs better or on-par with the existing baselines. To this end, we eliminate the necessity of determining the optimal value of the number of clusters and demonstrate that our method is more viable for large-scale classification tasks.