Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations
Kathleen Anderson, Thomas Martinetz
We evaluate the information that can unintentionally leak into the low dimensional output of a neural network, by reconstructing an input image from a 40- or 32-element feature vec…
cs.CV2024
Enhancing Generalization in Convolutional Neural Networks through Regularization with Edge and Line Features
Christoph Linse, Beatrice Brückner, Thomas Martinetz
This paper proposes a novel regularization approach to bias Convolutional Neural Networks (CNNs) toward utilizing edge and line features in their hidden layers. Rather than learnin…