Daniel Lehmann

Daniel Lehmann is a Ph.D. student and research assistant at the department of Computer Science of the University of Greifswald. In his Ph.D. he focuses on robust learning of neural network-based image classification models. His research interests include machine learning, out-of-distribution detection, and adversarial attacks. He holds a Diplom degree (comparable to a Master degree) in Business Computer Science from the University of Rostock.

• Daniel Lehmann and Marc Ebner
  Calculating the Credibility of Test Samples at Inference by a Layer-wise Activation Cluster Analysis of Convolutional Neural Networks.
  In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications, 12-14 July 2022, Lisbon, Portugal, Science and Technology Publications, 2022. (Best Paper Award)
  [Paper]

• Daniel Lehmann and Marc Ebner
  Subclass-based Undersampling for Class-imbalanced Image Classification.
  In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP, Science and Technology Publications, pp. 493--500, 2022.
  [Paper]

• Daniel Lehmann and Marc Ebner
  Layer-Wise Activation Cluster Analysis of CNNs to Detect Out-of-Distribution Samples.
  In Igor Farkas, Paolo Masulli, Sebastian Otte and Stefan Wermter (editors), Proceedings of the 30th International Conference on Artificial Neural Networks ICANN 2021, pp. 214-226, Springer, Berlin, 2021.
  [Paper]

• Daniel Lehmann and Marc Ebner
  Are Image Patches Beneficial for Initializing Convolutional Neural Network Models?. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP, pp. 346-353, Science and Technology Publications, 2021.
  [Paper]

• Einführung in die Informatik (Übung)
• Computergrafik I (Übung)
• Evolutionäre Algorithmen (Übung)
• Praktikum Softwaretechnik