Zobrazeno 1 - 10
of 542
pro vyhledávání: '"Moser, Brian 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
Capturing pupil diameter is essential for assessing psychological and physiological states such as stress levels and cognitive load. However, the low resolution of images in eye datasets often hampers precise measurement. This study evaluates the imp
Externí odkaz:
http://arxiv.org/abs/2408.10397
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
Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further pushed im
Externí odkaz:
http://arxiv.org/abs/2407.15507
In this work, we introduce EyeDentify, a dataset specifically designed for pupil diameter estimation based on webcam images. EyeDentify addresses the lack of available datasets for pupil diameter estimation, a crucial domain for understanding physiol
Externí odkaz:
http://arxiv.org/abs/2407.11204
Autor:
Brigljevic, Vuko, Ferencek, Dinko, Landsberg, Greg, Robens, Tania, Stamenkovic, Marko, Susa, Tatjana, Abouabid, Hamza, Arhrib, Abdesslam, Arnold, Hannah, Azevedo, Duarte, Diaz, Daniel, Duarte, Javier, Pree, Tristan du, Falaki, Jaouad El, Ferreira, Pedro. M., Fuks, Benjamin, Ganguly, Sanmay, Kolosova, Marina, Konigsberg, Jacobo, Liu, Bingxuan, Moser, Brian, Muehlleitner, Margarete, Papaefstathiou, Andreas, Pasechnik, Roman, Santos, Rui, Sheldon, Brian, Soyez, Gregory, Stylianou, Panagiotis, Tetlalmatzi-Xolocotzi, Gilberto, Weiglein, Georg, Zanderighi, Giulia, Zhang, Rui
Publikováno v:
Eur. Phys. J. C 84, 1183 (2024)
We here report on the progress of the HHH Workshop, that took place in Dubrovnik in July 2023. After the discovery of a particle that complies with the properties of the Higgs boson of the Standard Model, all SM parameters are in principle determined
Externí odkaz:
http://arxiv.org/abs/2407.03015
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