Moritz Böhle (PhD Student)

Personal Information

Publications

2024

  1. Conference paper
    D2
    “B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable,” in Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, Canada.
  2. Conference paper
    D2
    “Good Teachers Explain: Explanation-Enhanced Knowledge Distillation,” in Computer Vision -- ECCV 2024, Milano, Italy.
  3. Conference paper
    D2
    “Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery,” in Computer Vision -- ECCV 2024, Milan, Italy, 2024.
  4. Article
    D2
    “Better Understanding Differences in Attribution Methods via Systematic Evaluations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 6, 2024.
  5. Thesis
    D2IMPR-CS
    “Towards Designing Inherently Interpretable Deep Neural Networks for Image Classification,” Universität des Saarlandes, Saarbrücken, 2024.

2023

  1. Conference paper
    D2
    “Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data,” in Eleventh International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda, 2023.
  2. Conference paper
    D2
    “Studying How to Efficiently and Effectively Guide Models with Explanations,” in IEEE/CVF International Conference on Computer Vision (ICCV 2023), Paris, France, 2023.
  3. Article
    D2
    “Optimising for Interpretability: Convolutional Dynamic Alignment Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 6, 2023.
  4. Paper
    D2
    “Holistically Explainable Vision Transformers,” 2023. [Online]. Available: https://arxiv.org/abs/2301.08669.

2022

  1. Conference paper
    D2
    “B-cos Networks: Alignment is All We Need for Interpretability,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.
  2. Conference paper
    D4D2
    “Towards Better Understanding Attribution Methods,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 2022.

2021

  1. Conference paper
    D2
    “Convolutional Dynamic Alignment Networks for Interpretable Classifications,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), Nashville, TN, USA (Virtual), 2021.