Zobrazeno 1 - 10
of 835
pro vyhledávání: '"Alfarra, A"'
Autor:
S, Gabriel Pérez, Pérez, Juan C., Alfarra, Motasem, Zarzar, Jesús, Rojas, Sara, Ghanem, Bernard, Arbeláez, Pablo
This paper presents preliminary work on a novel connection between certified robustness in machine learning and the modeling of 3D objects. We highlight an intriguing link between the Maximal Certified Radius (MCR) of a classifier representing a spac
Externí odkaz:
http://arxiv.org/abs/2408.13135
Autor:
Alhamoud, Kumail, Ghunaim, Yasir, Alfarra, Motasem, Hartvigsen, Thomas, Torr, Philip, Ghanem, Bernard, Bibi, Adel, Ghassemi, Marzyeh
For medical imaging AI models to be clinically impactful, they must generalize. However, this goal is hindered by (i) diverse types of distribution shifts, such as temporal, demographic, and label shifts, and (ii) limited diversity in datasets that a
Externí odkaz:
http://arxiv.org/abs/2407.08822
Autor:
Yang, Yibo, Li, Xiaojie, Alfarra, Motasem, Hammoud, Hasan, Bibi, Adel, Torr, Philip, Ghanem, Bernard
Relieving the reliance of neural network training on a global back-propagation (BP) has emerged as a notable research topic due to the biological implausibility and huge memory consumption caused by BP. Among the existing solutions, local learning op
Externí odkaz:
http://arxiv.org/abs/2406.05222
Understanding videos that contain multiple modalities is crucial, especially in egocentric videos, where combining various sensory inputs significantly improves tasks like action recognition and moment localization. However, real-world applications o
Externí odkaz:
http://arxiv.org/abs/2404.15161
Autor:
Belal Aldabbour, Ayoub AbuNemer, Muhammed Ghazi Alfarra, Osama Aldabbour, Yousef Abu Zaydah, Haytham Abuzaid, Abd Al-Karim Sammour, Samah Elamassie, Ahmed Yassin
Publikováno v:
BMC Health Services Research, Vol 24, Iss 1, Pp 1-8 (2024)
Abstract Background Status epilepticus (SE) is a top neurological and medical emergency. Adequate staff knowledge and sufficient hospital resources are mandatory for timely management and better outcomes. This study aims to evaluate Palestinian ER do
Externí odkaz:
https://doaj.org/article/eee61780170a4018a19a1c61c260c5ee
Autor:
Alfarra, Motasem, Itani, Hani, Pardo, Alejandro, Alhuwaider, Shyma, Ramazanova, Merey, Pérez, Juan C., Cai, Zhipeng, Müller, Matthias, Ghanem, Bernard
This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to distributi
Externí odkaz:
http://arxiv.org/abs/2304.04795
Autor:
Houyon, Joachim, Cioppa, Anthony, Ghunaim, Yasir, Alfarra, Motasem, Halin, Anaïs, Henry, Maxim, Ghanem, Bernard, Van Droogenbroeck, Marc
In recent years, online distillation has emerged as a powerful technique for adapting real-time deep neural networks on the fly using a slow, but accurate teacher model. However, a major challenge in online distillation is catastrophic forgetting whe
Externí odkaz:
http://arxiv.org/abs/2304.01239
Autor:
Ghunaim, Yasir, Bibi, Adel, Alhamoud, Kumail, Alfarra, Motasem, Hammoud, Hasan Abed Al Kader, Prabhu, Ameya, Torr, Philip H. S., Ghanem, Bernard
Current evaluations of Continual Learning (CL) methods typically assume that there is no constraint on training time and computation. This is an unrealistic assumption for any real-world setting, which motivates us to propose: a practical real-time e
Externí odkaz:
http://arxiv.org/abs/2302.01047
Autor:
Villa, Andrés, Alcázar, Juan León, Alfarra, Motasem, Alhamoud, Kumail, Hurtado, Julio, Heilbron, Fabian Caba, Soto, Alvaro, Ghanem, Bernard
Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult or impossible to train and update large-scale models on such dynamic
Externí odkaz:
http://arxiv.org/abs/2212.04842
Continual Learning is a step towards lifelong intelligence where models continuously learn from recently collected data without forgetting previous knowledge. Existing continual learning approaches mostly focus on image classification in the class-in
Externí odkaz:
http://arxiv.org/abs/2211.16234