Matthias Körschens, M.Sc.
Matthias Körschens
Address: Biodiversität der Pflanzen
Institut für Ökologie und Evolution
Fakultät für Biowissenschaften
Friedrich-Schiller-Universität Jena
Philosophenweg 16
07743 Jena
Germany
Phone: +49 (0) 3641 9 49263
E-mail: matthias (dot) koerschens (at) uni-jena (dot) de
Room: 105
Links:
Curriculum Vitae
since 2019 PhD Student & Research Associate
Group “Biodiversität der Pflanzen”, Friedrich Schiller University Jena
Computer Vision Group, Friedrich Schiller University Jena
2018 – 2019 Research Assistant
Computer Vision Group, Friedrich Schiller University Jena
2016 – 2018 M. Sc. Computer Science
Friedrich Schiller University Jena
Master Thesis: “Identification in Wildlife Monitoring”
2012 – 2016 B. Sc. Computer Science
Harz University of Applied Studies, Wernigerode
Bachelor Thesis: “Simulation eines kapazitiven Sensors zur Geometriebestimmung
und -bewertung eines Katheters”
Research Interests
  • Deep Learning
  • Finegrained Classification & Detection
  • Unified Networks
  • Weakly Supervised Learning
  • Self-Supervised Learning
Publications
2024
Matthias Körschens, Solveig Franziska Bucher, Paul Bodesheim, Josephine Ulrich, Joachim Denzler, Christine Römermann:
Determining the Community Composition of Herbaceous Species from Images using Convolutional Neural Networks.
Ecological Informatics. 80 : pp. 102516. 2024.
[bibtex] [web] [doi] [abstract]
2023
Matthias Körschens, Solveig Franziska Bucher, Christine Römermann, Joachim Denzler:
Improving Data Efficiency for Plant Cover Prediction with Label Interpolation and Monte-Carlo Cropping.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). 2023.
[bibtex] [pdf] [web] [supplementary] [abstract]
Matthias Körschens, Solveig Franziska Bucher, Christine Römermann, Joachim Denzler:
Unified Automatic Plant Cover and Phenology Prediction.
ICCV Workshop on Computer Vision in Plant Phenotyping and Agriculture (CVPPA). 2023.
[bibtex] [pdf] [abstract]
2022
Matthias Körschens, Paul Bodesheim, Joachim Denzler:
Beyond Global Average Pooling: Alternative Feature Aggregations for Weakly Supervised Localization.
International Conference on Computer Vision Theory and Applications (VISAPP). Pages 180-191. 2022.
[bibtex] [pdf] [doi] [abstract]
Matthias Körschens, Paul Bodesheim, Joachim Denzler:
Occlusion-Robustness of Convolutional Neural Networks via Inverted Cutout.
International Conference on Pattern Recognition (ICPR). Pages 2829-2835. 2022.
[bibtex] [pdf] [doi] [supplementary] [abstract]
Paul Bodesheim, Jan Blunk, Matthias Körschens, Clemens-Alexander Brust, Christoph Käding, Joachim Denzler:
Pre-trained models are not enough: active and lifelong learning is important for long-term visual monitoring of mammals in biodiversity research. Individual identification and attribute prediction with image features from deep neural networks and decoupled decision models applied to elephants and great apes.
Mammalian Biology. 102 : pp. 875-897. 2022.
[bibtex] [web] [doi] [abstract]
2021
Bernd Gruner, Matthias Körschens, Björn Barz, Joachim Denzler:
Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity.
Findings of the CVPR Workshop on Continual Learning in Computer Vision (CLVision). 2021.
[bibtex] [abstract]
Matthias Körschens, Paul Bodesheim, Christine Römermann, Solveig Franziska Bucher, Mirco Migliavacca, Josephine Ulrich, Joachim Denzler:
Automatic Plant Cover Estimation with Convolutional Neural Networks.
Computer Science for Biodiversity Workshop (CS4Biodiversity), INFORMATIK 2021. Pages 499-516. 2021.
[bibtex] [pdf] [doi] [abstract]
Matthias Körschens, Paul Bodesheim, Christine Römermann, Solveig Franziska Bucher, Mirco Migliavacca, Josephine Ulrich, Joachim Denzler:
Weakly Supervised Segmentation Pretraining for Plant Cover Prediction.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 589-603. 2021.
[bibtex] [pdf] [doi] [supplementary] [abstract]
2020
Matthias Körschens, Paul Bodesheim, Christine Römermann, Solveig Franziska Bucher, Josephine Ulrich, Joachim Denzler:
Towards Confirmable Automated Plant Cover Determination.
ECCV Workshop on Computer Vision Problems in Plant Phenotyping (CVPPP). 2020.
[bibtex] [pdf] [web] [doi] [supplementary] [abstract]
2019
Matthias Körschens, Joachim Denzler:
ELPephants: A Fine-Grained Dataset for Elephant Re-Identification.
ICCV Workshop on Computer Vision for Wildlife Conservation (ICCV-WS). 2019.
[bibtex] [pdf] [abstract]
2018
Matthias Körschens, Björn Barz, Joachim Denzler:
Towards Automatic Identification of Elephants in the Wild.
AI for Wildlife Conservation Workshop (AIWC). 2018.
[bibtex] [pdf] [abstract]