Search Results for author: Reinhard Koch

Found 13 papers, 4 papers with code

Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels

no code implementations13 Oct 2021 Lars Schmarje, Reinhard Koch

We envision the incorporation of fuzzy labels into Semi-Supervised Learning and give a proof-of-concept of the potential lower costs and higher consistency in the complete development cycle.

Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy

1 code implementation13 Oct 2021 Lars Schmarje, Johannes Brünger, Monty Santarossa, Simon-Martin Schröder, Rainer Kiko, Reinhard Koch

We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels.

Learning Stixel-based Instance Segmentation

no code implementations7 Jul 2021 Monty Santarossa, Lukas Schneider, Claudius Zelenka, Lars Schmarje, Reinhard Koch, Uwe Franke

Stixels have been successfully applied to a wide range of vision tasks in autonomous driving, recently including instance segmentation.

Autonomous Driving Instance Segmentation +1

S2C2 -- An orthogonal method for Semi-Supervised Learning on ambiguous labels

no code implementations30 Jun 2021 Lars Schmarje, Monty Santarossa, Simon-Martin Schröder, Claudius Zelenka, Rainer Kiko, Jenny Stracke, Nina Volkmann, Reinhard Koch

Semi-Supervised Learning (SSL) can decrease the required amount of labeled image data and thus the cost for deep learning.

Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering

no code implementations3 Dec 2020 Lars Schmarje, Johannes Brünger, Monty Santarossa, Simon-Martin Schröder, Rainer Kiko, Reinhard Koch

We propose a novel loss to improve the overclustering capability of our framework and show on the common image classification dataset STL-10 that it is faster and has better overclustering performance than previous work.

General Classification Image Classification

An Analysis by Synthesis Method that Allows Accurate Spatial Modeling of Thickness of Cortical Bone from Clinical QCT

no code implementations18 Sep 2020 Stefan Reinhold, Timo Damm, Sebastian Büsse, Stanislav N. Gorb, Claus-C. Glüer, Reinhard Koch

Quantitative computed tomography (QCT) permits the selective analysis of cortical bone, however the low spatial resolution of clinical QCT leads to an overestimation of the thickness of cortical bone (Ct. Th) and bone strength.

Panoptic Instance Segmentation on Pigs

no code implementations21 May 2020 Johannes Brünger, Maria Gentz, Imke Traulsen, Reinhard Koch

In recent years, methods based on deep learning have been introduced and have shown pleasingly good results.

Instance Segmentation Panoptic Segmentation

MorphoCluster: Efficient Annotation of Plankton images by Clustering

1 code implementation4 May 2020 Simon-Martin Schröder, Rainer Kiko, Reinhard Koch

By aggregating similar images into clusters, our novel approach to image annotation increases consistency, multiplies the throughput of an annotator and allows experts to adapt the granularity of their sorting scheme to the structure in the data.

General Classification Object Classification

DRST: Deep Residual Shearlet Transform for Densely Sampled Light Field Reconstruction

no code implementations19 Mar 2020 Yuan Gao, Robert Bregovic, Reinhard Koch, Atanas Gotchev

Specifically, for an input sparsely-sampled EPI, DRST employs a deep fully Convolutional Neural Network (CNN) to predict the residuals of the shearlet coefficients in shearlet domain in order to reconstruct a densely-sampled EPI in image domain.

2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy

1 code implementation30 Jul 2019 Lars Schmarje, Claudius Zelenka, Ulf Geisen, Claus-C. Glüer, Reinhard Koch

Furthermore, we compare a variety of 2D and 3D methods such as classical approaches like Fourier analysis with state-of-the-art deep neural networks for the classification of local fiber orientations.

Restoration of Images with Wavefront Aberrations

no code implementations2 Apr 2017 Claudius Zelenka, Reinhard Koch

In most coherent imaging systems, especially in astronomy, the wavefront deformation is known.

Image Restoration

Cannot find the paper you are looking for? You can Submit a new open access paper.