3 papers
cs.LG2024
Continuous Learned Primal Dual
Christina Runkel, Ander Biguri, Carola-Bibiane Schönlieb
Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be dire…
cs.LG2021
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
Christina Runkel, Christian Etmann, Michael Möller +1
An increasing number of models require the control of the spectral norm of convolutional layers of a neural network. While there is an abundance of methods for estimating and enfor…
cs.CV2020
Exploiting the Logits: Joint Sign Language Recognition and Spell-Correction
Christina Runkel, Stefan Dorenkamp, Hartmut Bauermeister +1
Machine learning techniques have excelled in the automatic semantic analysis of images, reaching human-level performances on challenging benchmarks. Yet, the semantic analysis of v…