Browsing Fakultet for ingeniør- og naturvitskap / Faculty of Engineering and Science by Author "Sagemüller, Justus"

Now showing items 1-2 of 2

    • Ablation Path Saliency 

      Sagemüller, Justus; Verdier, Olivier Philippe Paul (Peer reviewed; Journal article, 2023)
      Various types of saliency methods have been proposed for explaining black-box classification. In image applications, this means highlighting the part of the image that is most relevant for the current decision. Unfortunately, ...

    • Paths towards reliable explainability: In neural networks for image-processing 

      Sagemüller, Justus (Doctoral thesis, 2024)
      Machine learning systems (often referred to as AI, not always appropriately) are increasingly used in varied applications, including ones with strong impact on human lives. While this is expected to bring economic and ...