Pu­bli­ka­tio­nen

[ 2022 ] [ 2021 ] [ 2020 ] [ 2019 ] [ 2018 ] [ 2017 ]

2022 [ nach oben ]

  • 1.
    Herde, M., Huang, Z., Huseljic, D., Kottke, D., Vogt, S., Sick, B.: Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning. arXiv e-prints. arXiv:2210.06112 (2022).
     
  • 2.
    Rauch, L., Huseljic, D., Sick, B.: Enhancing Active Learning with Weak Supervision and Transfer Learning by Leveraging Information and Knowledge Sources. Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. bll. 27–42 (2022).
     
  • 3.
    Huseljic, D., Herde, M., Muejde, M., Sick, B.: A Review of Uncertainty Calibration in Pretrained Object Detectors. arXiv e-prints. arXiv:2210.02935 (2022).
     
  • 4.
    Herde, M., Huseljic, D., Mitrovic, J., Granitzer, M., Sick, B.: A Concept for Automated Polarized Web Content Annotation based on Multimodal Active Learning. Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. bll. 1–6 (2022).
     

2021 [ nach oben ]

  • 1.
    Kottke, D., Herde, M., Sandrock, C., Huseljic, D., Krempl, G., Sick, B.: Toward optimal probabilistic active learning using a Bayesian approach. Machine Learning. 110, 1199–1231 (2021).
     
  • 2.
    Huseljic, D., Sick, B., Herde, M., Kottke, D.: Separation of Aleatoric and Epistemic Uncertainty in Deterministic Deep Neural Networks. International Conference on Pattern Recognition (ICPR). bll. 9172–9179. IEEE (2021).
     
  • 3.
    Möller, F., Botache, D., Huseljic, D., Heidecker, F., Bieshaar, M., Sick, B.: Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders. Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD), CVPR. bll. 1–10 (2021).
     
  • 4.
    Herde, M., Kottke, D., Huseljic, D., Sick, B.: Multi-annotator Probabilistic Active Learning. International Conference on Pattern Recognition (ICPR). bll. 10281–10288. IEEE (2021).
     
  • 5.
    Herde, M., Huseljic, D., Sick, B., Calma, A.: A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification. IEEE Access. 9, 166970–166989 (2021).
     

2020 [ nach oben ]

  • 1.
    Kottke, D., Herde, M., Sandrock, C., Huseljic, D., Krempl, G., Sick, B.: Toward Optimal Probabilistic Active Learning Using a Bayesian Approach. arXiv e-prints. arXiv:2006.01732 (2020).
     

2019 [ nach oben ]

  • 1.
    Kottke, D., Schellinger, J., Huseljic, D., Sick, B.: Limitations of Assessing Active Learning Performance at Runtime. arXiv e-prints. arXiv:1901.10338 (2019).
     

2018 [ nach oben ]

  • 1.
    Tomforde, S., Dehling, T., Haux, R., Huseljic, D., Kottke, D., Scheerbaum, J., Sick, B., Sunyaev, A., Wolf, K.-H.: Towards Proactive Health-enabling Living Environments: Simulation-based Study and Research Challenges. International Workshop on Self-optimisation in Organic and Autonomic Computing Systems (SAOS), ARCS. bll. 1–8. VDE (2018).
     
  • 2.
    Kottke, D., Calma, A., Huseljic, D., Sandrock, C., Kachergis, G., Sick, B.: The Other Human in The Loop -- A Pilot Study to Find Selection Strategies for Active Learning. International Joint Conference on Neural Networks (IJCNN). IEEE, Rio de Janiero, Brazil (2018).
     

2017 [ nach oben ]

  • 1.
    Kottke, D., Calma, A., Huseljic, D., Krempl, G., Sick, B.: Challenges of Reliable, Realistic and Comparable Active Learning Evaluation. Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. bll. 2–14 (2017).