Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Ardizzone, Lynton"'
Autor:
Adler, Tim J., Nölke, Jan-Hinrich, Reinke, Annika, Tizabi, Minu Dietlinde, Gruber, Sebastian, Trofimova, Dasha, Ardizzone, Lynton, Jaeger, Paul F., Buettner, Florian, Köthe, Ullrich, Maier-Hein, Lena
Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, posterior-based methods such as conditional Diffusion Models and Invertible
Externí odkaz:
http://arxiv.org/abs/2309.09764
Publikováno v:
In: Fink, G., Frintrop, S., Jiang, X. (eds) Pattern Recognition. DAGM GCPR 2019. Lecture Notes in Computer Science, vol 11824. Springer, Cham
Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work, we present methods to train Invertible Neural Networks (INNs) as (vari
Externí odkaz:
http://arxiv.org/abs/2303.11239
Autor:
Kang, Da Eun, Klessen, Ralf S., Ksoll, Victor F., Ardizzone, Lynton, Koethe, Ullrich, Glover, Simon C. O.
Stellar feedback, the energetic interaction between young stars and their birthplace, plays an important role in the star formation history of the universe and the evolution of the interstellar medium (ISM). Correctly interpreting the observations of
Externí odkaz:
http://arxiv.org/abs/2301.03014
Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation methods eit
Externí odkaz:
http://arxiv.org/abs/2203.16542
Deep neural networks are commonly used for medical purposes such as image generation, segmentation, or classification. Besides this, they are often criticized as black boxes as their decision process is often not human interpretable. Encouraging the
Externí odkaz:
http://arxiv.org/abs/2203.11132
Autor:
Haldemann, Jonas, Ksoll, Victor, Walter, Daniel, Alibert, Yann, Klessen, Ralf S., Benz, Willy, Koethe, Ullrich, Ardizzone, Lynton, Rother, Carsten
Publikováno v:
A&A 672, A180 (2023)
The characterization of an exoplanet's interior is an inverse problem, which requires statistical methods such as Bayesian inference in order to be solved. Current methods employ Markov Chain Monte Carlo (MCMC) sampling to infer the posterior probabi
Externí odkaz:
http://arxiv.org/abs/2202.00027
Autor:
Kang, Da Eun, Pellegrini, Eric W., Ardizzone, Lynton, Klessen, Ralf S., Koethe, Ullrich, Glover, Simon C. O., Ksoll, Victor F.
Young massive stars play an important role in the evolution of the interstellar medium (ISM) and the self-regulation of star formation in giant molecular clouds (GMCs) by injecting energy, momentum, and radiation (stellar feedback) into surrounding e
Externí odkaz:
http://arxiv.org/abs/2201.08765
Autor:
Ardizzone, Lynton, Kruse, Jakob, Lüth, Carsten, Bracher, Niels, Rother, Carsten, Köthe, Ullrich
We introduce a new architecture called a conditional invertible neural network (cINN), and use it to address the task of diverse image-to-image translation for natural images. This is not easily possible with existing INN models due to some fundament
Externí odkaz:
http://arxiv.org/abs/2105.02104
Publikováno v:
Workshop on Invertible Neural Networks and Normalizing Flows (ICML 2019)
Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten invertible architectures and related models fare on two intuitive, low-dimens
Externí odkaz:
http://arxiv.org/abs/2101.10763
Autor:
Trofimova, Darya, Adler, Tim, Kausch, Lisa, Ardizzone, Lynton, Maier-Hein, Klaus, Köthe, Ulrich, Rother, Carsten, Maier-Hein, Lena
Image registration is the basis for many applications in the fields of medical image computing and computer assisted interventions. One example is the registration of 2D X-ray images with preoperative three-dimensional computed tomography (CT) images
Externí odkaz:
http://arxiv.org/abs/2012.08195