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 April 2019: PhD Student & research associate at the group “Biodiversität der Pflanzen” of the Friedrich Schiller University Jena
  • August 2018-March 2019: Scientific Assistant at the Computer Vision Group of the Friedrich Schiller University Jena
  • May 2018: Master Thesis with title: “Identification in Wildlife Monitoring”
  • April 2016-May 2018: Master Student in Computer Science at the Friedrich Schiller University Jena
  • February 2016: Bachelor Thesis with title “Simulation eines kapazitiven Sensors zur Geometriebestimmung und -bewertung eines Katheters”
  • September 2012-February 2016: Bachelor Student in Computer Science at Hochschule Harz in Wernigerode
  • Juli 2012: Abitur at the Domgymnasium Merseburg
Research Interests
  • Deep Learning
  • Finegrained Classification & Detection
  • Unified Networks
  • Weakly Supervised Learning
  • Self-Supervised Learning
Publications
2022
Beyond Global Average Pooling: Alternative Feature Aggregations for Weakly Supervised Localization
Matthias Körschens and Paul Bodesheim and Joachim Denzler.
International Conference on Computer Vision Theory and Applications (VISAPP). Pages 180-191. 2022.
[bibtex] [pdf] [abstract]
Occlusion-Robustness of Convolutional Neural Networks via Inverted Cutout
Matthias Körschens and Paul Bodesheim and Joachim Denzler.
International Conference on Pattern Recognition (ICPR). 2022.
[bibtex] [pdf] [supplementary] [abstract]
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
Paul Bodesheim and Jan Blunk and Matthias Körschens and Clemens-Alexander Brust and Christoph Käding and Joachim Denzler.
Mammalian Biology. 2022.
[bibtex] [web] [abstract]
2021
Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity
Bernd Gruner and Matthias Körschens and Björn Barz and Joachim Denzler.
Findings of the CVPR Workshop on Continual Learning in Computer Vision (CLVision). 2021.
[bibtex] [abstract]
Automatic Plant Cover Estimation with Convolutional Neural Networks
Matthias Körschens and Paul Bodesheim and Christine Römermann and Solveig Franziska Bucher and Mirco Migliavacca and Josephine Ulrich and Joachim Denzler.
Computer Science for Biodiversity Workshop (CS4Biodiversity), INFORMATIK 2021. Pages 499-516. 2021.
[bibtex] [pdf] [abstract]
Weakly Supervised Segmentation Pretraining for Plant Cover Prediction
Matthias Körschens and Paul Bodesheim and Christine Römermann and Solveig Franziska Bucher and Mirco Migliavacca and Josephine Ulrich and Joachim Denzler.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 589-603. 2021.
[bibtex] [pdf] [supplementary] [abstract]
2020
Towards Confirmable Automated Plant Cover Determination
Matthias Körschens and Paul Bodesheim and Christine Römermann and Solveig Franziska Bucher and Josephine Ulrich and Joachim Denzler.
ECCV Workshop on Computer Vision Problems in Plant Phenotyping (CVPPP). 2020.
[bibtex] [pdf] [web] [supplementary] [abstract]
2019
ELPephants: A Fine-Grained Dataset for Elephant Re-Identification
Matthias Körschens and Joachim Denzler.
ICCV Workshop on Computer Vision for Wildlife Conservation (ICCV-WS). 2019.
[bibtex] [pdf] [abstract]
2018
Towards Automatic Identification of Elephants in the Wild
Matthias Körschens and Björn Barz and Joachim Denzler.
AI for Wildlife Conservation Workshop (AIWC). 2018.
[bibtex] [pdf] [abstract]