Zobrazeno 1 - 10
of 2 850
pro vyhledávání: '"Kainz P"'
Generative methods now produce outputs nearly indistinguishable from real data but often fail to fully capture the data distribution. Unlike quality issues, diversity limitations in generative models are hard to detect visually, requiring specific me
Externí odkaz:
http://arxiv.org/abs/2411.16171
Latent Video Diffusion Models can easily deceive casual observers and domain experts alike thanks to the produced image quality and temporal consistency. Beyond entertainment, this creates opportunities around safe data sharing of fully synthetic dat
Externí odkaz:
http://arxiv.org/abs/2411.04956
Autor:
Kainz, Nicolas, Lebiedz, Dirk
In this follow-up paper to [Local geometry of Equilibria and a Poincare-Bendixson-type Theorem for Holomorphic Flows, Nicolas Kainz, Dirk Lebiedz (2024)] we investigate the global topology and geometry of dynamical systems $\dot{x} = F(x)$ with entir
Externí odkaz:
http://arxiv.org/abs/2410.04895
Although powerful for image generation, consistent and controllable video is a longstanding problem for diffusion models. Video models require extensive training and computational resources, leading to high costs and large environmental impacts. More
Externí odkaz:
http://arxiv.org/abs/2410.05322
Autor:
Kainz, Johannes, Makwana, Nikitabahen N., Kumar, Bipin, Ravichandran, S., Fries, Johan, Sardina, Gaetano, Mehlig, Bernhard, Hoffmann, Fabian
Considering turbulence is crucial to understanding clouds. However, covering all scales involved in the turbulent mixing of clouds with their environment is computationally challenging, urging the development of simpler models to represent some of th
Externí odkaz:
http://arxiv.org/abs/2410.03789
Large Language Models (LLMs) often produce outputs that -- though plausible -- can lack consistency and reliability, particularly in ambiguous or complex scenarios. Challenges arise from ensuring that outputs align with both factual correctness and h
Externí odkaz:
http://arxiv.org/abs/2410.01064
Autor:
Prenner, Andrea, Kainz, Bernhard
Machine Learning (ML) models have gained popularity in medical imaging analysis given their expert level performance in many medical domains. To enhance the trustworthiness, acceptance, and regulatory compliance of medical imaging models and to facil
Externí odkaz:
http://arxiv.org/abs/2409.17800
Autor:
Reynaud, Hadrien, Baugh, Matthew, Dombrowski, Mischa, Cechnicka, Sarah, Meng, Qingjie, Kainz, Bernhard
We introduce the Joint Video-Image Diffusion model (JVID), a novel approach to generating high-quality and temporally coherent videos. We achieve this by integrating two diffusion models: a Latent Image Diffusion Model (LIDM) trained on images and a
Externí odkaz:
http://arxiv.org/abs/2409.14149
Autor:
Li, Liu, Wang, Hanchun, Baugh, Matthew, Ma, Qiang, Zhang, Weitong, Ouyang, Cheng, Rueckert, Daniel, Kainz, Bernhard
Although existing medical image segmentation methods provide impressive pixel-wise accuracy, they often neglect topological correctness, making their segmentations unusable for many downstream tasks. One option is to retrain such models whilst includ
Externí odkaz:
http://arxiv.org/abs/2409.09796
While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge. Dataset distillation addresses these challenges by synthesizing only a few im
Externí odkaz:
http://arxiv.org/abs/2409.03929