Zobrazeno 1 - 10
of 6 486
pro vyhledávání: '"Ribeiro, A. De A."'
Autor:
Jones, Charles, Ribeiro, Fabio de Sousa, Roschewitz, Mélanie, Castro, Daniel C., Glocker, Ben
We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions inherent to these methods. We p
Externí odkaz:
http://arxiv.org/abs/2410.04120
Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive pairs. Positive
Externí odkaz:
http://arxiv.org/abs/2409.10365
Autor:
Peng, Wei, Xia, Tian, Ribeiro, Fabio De Sousa, Bosschieter, Tomas, Adeli, Ehsan, Zhao, Qingyu, Glocker, Ben, Pohl, Kilian M.
The number of samples in structural brain MRI studies is often too small to properly train deep learning models. Generative models show promise in addressing this issue by effectively learning the data distribution and generating high-fidelity MRI. H
Externí odkaz:
http://arxiv.org/abs/2409.05585
Autor:
Kori, Avinash, Locatello, Francesco, Santhirasekaram, Ainkaran, Toni, Francesca, Glocker, Ben, Ribeiro, Fabio De Sousa
Learning modular object-centric representations is crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped. Understand
Externí odkaz:
http://arxiv.org/abs/2406.07141
Causal generative modelling is gaining interest in medical imaging due to its ability to answer interventional and counterfactual queries. Most work focuses on generating counterfactual images that look plausible, using auxiliary classifiers to enfor
Externí odkaz:
http://arxiv.org/abs/2403.09422
Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings. However, it is sensitive to the choice of augmentation pipeline. Positive pairs should preserve semantic info
Externí odkaz:
http://arxiv.org/abs/2403.09605
Autor:
Ribeiro, Fabio De Sousa, Glocker, Ben
Despite the growing popularity of diffusion models, gaining a deep understanding of the model class remains somewhat elusive for the uninitiated in non-equilibrium statistical physics. With that in mind, we present what we believe is a more straightf
Externí odkaz:
http://arxiv.org/abs/2401.06281
Autor:
Arbash, Elias, Ribeiro, Andréa de Lima, Thiele, Sam, Gnann, Nina, Rasti, Behnood, Fuchs, Margret, Ghamisi, Pedram, Gloaguen, Richard
The presence of undesired background areas associated with potential noise and unknown spectral characteristics degrades the performance of hyperspectral data processing. Masking out unwanted regions is key to addressing this issue. Processing only r
Externí odkaz:
http://arxiv.org/abs/2311.03053
Autor:
Koirala, Bikram, Rasti, Behnood, Bnoulkacem, Zakaria, Ribeiro, Andrea de Lima, Madriz, Yuleika, Herrmann, Erik, Gestels, Arthur, De Kerf, Thomas, Lorenz, Sandra, Fuchs, Margret, Janssens, Koen, Steenackers, Gunther, Gloaguen, Richard, Scheunders, Paul
Optical hyperspectral cameras capture the spectral reflectance of materials. Since many materials behave as heterogeneous intimate mixtures with which each photon interacts differently, the relationship between spectral reflectance and material compo
Externí odkaz:
http://arxiv.org/abs/2309.03216
Autor:
Jones, Charles, Castro, Daniel C., Ribeiro, Fabio De Sousa, Oktay, Ozan, McCradden, Melissa, Glocker, Ben
As machine learning methods gain prominence within clinical decision-making, addressing fairness concerns becomes increasingly urgent. Despite considerable work dedicated to detecting and ameliorating algorithmic bias, today's methods are deficient w
Externí odkaz:
http://arxiv.org/abs/2307.16526