31 code implementations • 25 Mar 2023 • Kilian Batzner, Lars Heckler, Rebecca König
We train a student network to predict the extracted features of normal, i. e., anomaly-free training images.
Ranked #2 on Anomaly Detection on MVTec AD (using extra training data)
Computational Efficiency Semi-supervised Anomaly Detection +1
no code implementations • 11 Nov 2020 • Rebecca König, Bertram Drost
We propose a method for 6DoF pose estimation of rigid objects that uses a state-of-the-art deep learning based instance detector to segment object instances in an RGB image, followed by a point-pair based voting method to recover the object's pose.
no code implementations • 18 Nov 2019 • Patrick Follmann, Rebecca König
State-of-the-art instance-aware semantic segmentation algorithms use axis-aligned bounding boxes as an intermediate processing step to infer the final instance mask output.
2 code implementations • 24 Apr 2018 • Patrick Follmann, Rebecca König, Philipp Härtinger, Michael Klostermann
Semantic amodal segmentation is a recently proposed extension to instance-aware segmentation that includes the prediction of the invisible region of each object instance.
no code implementations • ECCV 2018 • Patrick Follmann, Tobias Böttger, Philipp Härtinger, Rebecca König, Markus Ulrich
The dataset covers several challenges highly relevant in the field, such as a limited amount of training data and a high diversity in the test and validation sets.