Contextualised Out-of-Distribution Detection using Pattern Identication
R Xu-Darme, J Girard-Satabin, D Hond… - arXiv preprint arXiv …, 2023 - arxiv.org
arXiv preprint arXiv:2311.12855, 2023•arxiv.org
In this work, we propose CODE, an extension of existing work from the field of explainable AI
that identifies class-specific recurring patterns to build a robust Out-of-Distribution (OoD)
detection method for visual classifiers. CODE does not require any classifier retraining and
is OoD-agnostic, ie, tuned directly to the training dataset. Crucially, pattern identification
allows us to provide images from the In-Distribution (ID) dataset as reference data to provide
additional context to the confidence scores. In addition, we introduce a new benchmark …
that identifies class-specific recurring patterns to build a robust Out-of-Distribution (OoD)
detection method for visual classifiers. CODE does not require any classifier retraining and
is OoD-agnostic, ie, tuned directly to the training dataset. Crucially, pattern identification
allows us to provide images from the In-Distribution (ID) dataset as reference data to provide
additional context to the confidence scores. In addition, we introduce a new benchmark …
In this work, we propose CODE, an extension of existing work from the field of explainable AI that identifies class-specific recurring patterns to build a robust Out-of-Distribution (OoD) detection method for visual classifiers. CODE does not require any classifier retraining and is OoD-agnostic, i.e., tuned directly to the training dataset. Crucially, pattern identification allows us to provide images from the In-Distribution (ID) dataset as reference data to provide additional context to the confidence scores. In addition, we introduce a new benchmark based on perturbations of the ID dataset that provides a known and quantifiable measure of the discrepancy between the ID and OoD datasets serving as a reference value for the comparison between OoD detection methods.
arxiv.org