Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Almakky, A."'
Weight-averaged model-merging has emerged as a powerful approach in deep learning, capable of enhancing model performance without fine-tuning or retraining. However, the underlying mechanisms that explain its effectiveness remain largely unexplored.
Externí odkaz:
http://arxiv.org/abs/2411.09263
Autor:
Qazi, Mohammad Areeb, Hashmi, Anees Ur Rehman, Sanjeev, Santosh, Almakky, Ibrahim, Saeed, Numan, Gonzalez, Camila, Yaqub, Mohammad
Deep Learning has shown great success in reshaping medical imaging, yet it faces numerous challenges hindering widespread application. Issues like catastrophic forgetting and distribution shifts in the continuously evolving data stream increase the g
Externí odkaz:
http://arxiv.org/abs/2405.13482
Autor:
Qazi, Mohammad Areeb, Almakky, Ibrahim, Hashmi, Anees Ur Rehman, Sanjeev, Santosh, Yaqub, Mohammad
Continual learning, the ability to acquire knowledge from new data while retaining previously learned information, is a fundamental challenge in machine learning. Various approaches, including memory replay, knowledge distillation, model regularizati
Externí odkaz:
http://arxiv.org/abs/2404.14099
Autor:
Sanjeev, Santosh, Zhaksylyk, Nuren, Almakky, Ibrahim, Hashmi, Anees Ur Rehman, Qazi, Mohammad Areeb, Yaqub, Mohammad
The scarcity of well-annotated medical datasets requires leveraging transfer learning from broader datasets like ImageNet or pre-trained models like CLIP. Model soups averages multiple fine-tuned models aiming to improve performance on In-Domain (ID)
Externí odkaz:
http://arxiv.org/abs/2403.13341
Autor:
Sanjeev, Santosh, Maani, Fadillah Adamsyah, Abzhanov, Arsen, Papineni, Vijay Ram, Almakky, Ibrahim, Papież, Bartłomiej W., Yaqub, Mohammad
With the emergence of vision language models in the medical imaging domain, numerous studies have focused on two dominant research activities: (1) report generation from Chest X-rays (CXR), and (2) synthetic scan generation from text or reports. Desp
Externí odkaz:
http://arxiv.org/abs/2403.13343
Autor:
Almakky, Ibrahim, Sanjeev, Santosh, Hashmi, Anees Ur Rehman, Qazi, Mohammad Areeb, Yaqub, Mohammad
Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible performance ga
Externí odkaz:
http://arxiv.org/abs/2403.11646
Autor:
Hashmi, Anees Ur Rehman, Almakky, Ibrahim, Qazi, Mohammad Areeb, Sanjeev, Santosh, Papineni, Vijay Ram, Jagdish, Jagalpathy, Yaqub, Mohammad
Large-scale generative models have demonstrated impressive capabilities in producing visually compelling images, with increasing applications in medical imaging. However, they continue to grapple with hallucination challenges and the generation of an
Externí odkaz:
http://arxiv.org/abs/2403.09240
Autor:
Qazi, Mohammad Areeb, Alam, Mohammed Talha, Almakky, Ibrahim, Diehl, Werner Gerhard, Bricker, Leanne, Yaqub, Mohammad
Precise estimation of fetal biometry parameters from ultrasound images is vital for evaluating fetal growth, monitoring health, and identifying potential complications reliably. However, the automated computerized segmentation of the fetal head, abdo
Externí odkaz:
http://arxiv.org/abs/2311.09607
Autor:
Sanjeev, Santosh, Khatib, Salwa K. Al, Shaaban, Mai A., Almakky, Ibrahim, Papineni, Vijay Ram, Yaqub, Mohammad
Previous deep learning efforts have focused on improving the performance of Pulmonary Embolism(PE) diagnosis from Computed Tomography (CT) scans using Convolutional Neural Networks (CNN). However, the features from CT scans alone are not always suffi
Externí odkaz:
http://arxiv.org/abs/2308.14050
Lack of generalization to unseen domains/attacks is the Achilles heel of most face presentation attack detection (FacePAD) algorithms. Existing attempts to enhance the generalizability of FacePAD solutions assume that data from multiple source domain
Externí odkaz:
http://arxiv.org/abs/2308.10236