ODD Workshop

ALT (a) In sensory anomaly detection, test images with covariate shift will be considered as OOD. (b) In semantic anomaly detection and one-class novelty detection, normality/ID images belong to one class. Test images with semantic shift will be considered as OOD. (c) In multi-class novelty detection, ID images belong to multiple classes. Test images with semantic shift will be considered as OOD. (d) Open set recognition is identical to multi-class novelty detection in the task of detection, with the only difference that open set recognition further requires in-distribution classification. (e) Out-of-distribution detection is a super-category that covers semantic AD, one-class ND, multi-class ND, and open-set recognition, which canonically aims to detect test samples with semantic shift without losing the ID classification accuracy. (6) Outlier detection requires all observations and it defines the majority distribution as ID. Outliers can have any distribution shift.

ALT Taxonomy of generalized OOD detection framework. Four bases are used for the task taxonomy: (1) Distribution shift to detect: the task focuses on detecting covariate shift or semantic shift; (2) ID data type: the ID data contains one single class or multiple classes; (3) Whether the task requires ID classification; (4) Transductive learning task requires all observations; inductive tasks follow the train-test scheme. Note that OOD detection can encompass a broader spectrum of learning tasks, and go beyond multi-class classification.