Authors:
Oliver Rippel
1
;
Sergen Gülçelik
1
;
Khosrow Rahimi
2
;
Juliana Kurniadi
2
;
Andreas Herrmann
2
and
Dorit Merhof
1
Affiliations:
1
Institute of Imaging & Computer Vision, RWTH Aachen University, Aachen, Germany
;
2
DWI – Leibniz-Institut für Interaktive Materialien, Aachen, Germany
Keyword(s):
Out-of-Distribution Detection, Natural Fiber Identification, Classification, Open Set Recognition, Machine Learning.
Abstract:
Animal fiber identification is an essential aspect of fabric production, since specialty fibers such as cashmere are often targeted by adulteration attempts. Proposed, automated solutions can furthermore not be applied in practice (i.e. under the open set condition), as they are trained on a small subset of all existing fiber types only and simultaneously lack the ability to reject fiber types unseen during training at test time. In our work, we overcome this limitation by applying out-of-distribution (OOD)-detection techniques to the natural fiber identification task. Specifically, we propose to jointly model the probability density function of in-distribution data across feature levels of the trained classification network by means of Gaussian mixture models. Moreover, we extend the open set F-measure to the so-called area under the open set precision-recall curve (AUPRos), a threshold-independent measure of joint in-distribution classification & OOD-detection performance for OOD-d
etection methods with continuous OOD scores. Exhaustive comparison to the state of the art reveals that our proposed approach performs best overall, achieving highest area under the class-averaged, open set precision-recall curve (AUPRos,avg). We thus show that the application of automated fiber identification solutions under the open set condition is feasible via OOD detection.
(More)