no code implementations • 4 Apr 2024 • Simon Klüttermann, Emmanuel Müller
In this paper, we introduce DOUST, our method applying test-time training for outlier detection, significantly improving the detection performance.
no code implementations • 19 Mar 2024 • Simon Klüttermann, Jérôme Rutinowski, Anh Nguyen, Britta Grimme, Moritz Roidl, Emmanuel Müller
In this contribution, we introduce a novel ensemble method for the re-identification of industrial entities, using images of chipwood pallets and galvanized metal plates as dataset examples.