Zobrazeno 1 - 10
of 6 066
pro vyhledávání: '"Raue, A."'
Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel "Prune First, Distill After" framework that sy
Externí odkaz:
http://arxiv.org/abs/2411.12115
Autor:
Shanbhag, Arundhati S., Moser, Brian B., Nauen, Tobias C., Frolov, Stanislav, Raue, Federico, Dengel, Andreas
Diffusion models, known for their generative capabilities, have recently shown unexpected potential in image classification tasks by using Bayes' theorem. However, most diffusion classifiers require evaluating all class labels for a single classifica
Externí odkaz:
http://arxiv.org/abs/2411.12073
Large-scale, pre-trained Text-to-Image (T2I) diffusion models have gained significant popularity in image generation tasks and have shown unexpected potential in image Super-Resolution (SR). However, most existing T2I diffusion models are trained wit
Externí odkaz:
http://arxiv.org/abs/2411.12072
Autor:
Nagaraju, Sanath Budakegowdanadoddi, Moser, Brian Bernhard, Nauen, Tobias Christian, Frolov, Stanislav, Raue, Federico, Dengel, Andreas
Transformer-based Super-Resolution (SR) models have recently advanced image reconstruction quality, yet challenges remain due to computational complexity and an over-reliance on large patch sizes, which constrain fine-grained detail enhancement. In t
Externí odkaz:
http://arxiv.org/abs/2411.10231
Autor:
Anwar, Ahmed, Moser, Brian, Herurkar, Dayananda, Raue, Federico, Hegiste, Vinit, Legler, Tatjana, Dengel, Andreas
The emergence of federated learning (FL) presents a promising approach to leverage decentralized data while preserving privacy. Furthermore, the combination of FL and anomaly detection is particularly compelling because it allows for detecting rare a
Externí odkaz:
http://arxiv.org/abs/2408.04442
Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the
Externí odkaz:
http://arxiv.org/abs/2404.17670
In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset pruning to solve
Externí odkaz:
http://arxiv.org/abs/2403.17083
Machine learning traditionally relies on increasingly larger datasets. Yet, such datasets pose major storage challenges and usually contain non-influential samples, which could be ignored during training without negatively impacting the training qual
Externí odkaz:
http://arxiv.org/abs/2403.03881
Autor:
Moser, Brian B., Shanbhag, Arundhati S., Raue, Federico, Frolov, Stanislav, Palacio, Sebastian, Dengel, Andreas
Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of
Externí odkaz:
http://arxiv.org/abs/2401.00736
Autor:
Raue, Patrick J., Seresinhe, Kiana
Publikováno v:
Generations: Journal of the American Society on Aging, 2024 Apr 01. 48(1), 1-9.
Externí odkaz:
https://www.jstor.org/stable/48794565
