3 papers
cs.CV2024
Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach
Lars Nieradzik, Henrike Stephani, Janis Keuper
In this paper, we present an approach for evaluating attribution maps, which play a central role in interpreting the predictions of convolutional neural networks (CNNs). We show th…
cs.CV2024
WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images
Lars Nieradzik, Henrike Stephani, Jördis Sieburg-Rockel +4
Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper intro…
cs.CV2024
Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
Lars Nieradzik, Henrike Stephani, Janis Keuper
This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks. By constraining the spatial size o…