Constantin Kühne
  • CV
  • Projects
Categories
All (4)
Bayesian (1)
Computer Vision (2)
Contrastive Learning (1)
Deep Learning (3)
Diffusion Models (1)
Factor Graph (1)
Gaussian (1)
Image Segmentation (1)
Reinforcement Learning (1)
Representation Learning (1)

Projects

Beyond Balanced: Learning Static Search Trees with Tree-MDPs

Reinforcement Learning
Deep Learning
Beyond Balanced: Learning Static Search Trees with Tree-MDPs
May 25, 2025
Konrad Gerlach, Till Zemann, Constantin Kühne, Hendrik Droste, Alexander Kastius, Rainer Schlosser and Ralf Herbrich

TrueSkill Beyond Gaussians

Factor Graph
Bayesian
Gaussian
This master project researches message passing (MP) on factor graphs by incorporating richer distributions beyond the standard Gaussian approximation. Our goal is to improve…
Mar 5, 2025
Cedric Lorenz, Nick Bessin, Nina Burdorf, Till Zemann, Isabel Kurth, Lucas Kerschke, Constantin Kühne and Paul Ermler

InterpolationsDDPMGif

Learning Disentangled Representations with Identifiable Diffusion Models

Computer Vision
Deep Learning
Representation Learning
Diffusion Models
This work introduces a novel framework that combines the Denoising Diffusion Probabilistic Model (DDPM) with an identifiable Variational Autoencoder (iVAE) for disentangled…
Sep 16, 2024
Constantin Kühne and Till Zemann

heatmaps_pred

Automatic Bar Detection with Decoupled Heatmap-Embedding Learning

Computer Vision
Deep Learning
Contrastive Learning
Image Segmentation
This repository contains a suite of models based on U-Net variants and the Swin Transformer for image segmentation. The segmentation outputs are a probability heatmap for…
Mar 12, 2024
Kühne, Constantin and Postnov, Kirill and Schulze Tast, Johann and Treykorn, Felix and Zemann, Till
No matching items