Zobrazeno 1 - 10
of 220
pro vyhledávání: '"Pal, Arghya"'
Autor:
Loo, Junn Yong, Adeline, Michelle, Pal, Arghya, Baskaran, Vishnu Monn, Ting, Chee-Ming, Phan, Raphael C. -W.
Energy based models (EBMs) are appealing for their generality and simplicity in data likelihood modeling, but have conventionally been difficult to train due to the unstable and time-consuming implicit MCMC sampling during contrastive divergence trai
Externí odkaz:
http://arxiv.org/abs/2407.15238
Autor:
Jandial, Surgan, Khasbage, Yash, Pal, Arghya, Balasubramanian, Vineeth N, Krishnamurthy, Balaji
Publikováno v:
ECCV 2022
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature. Recent work Nasty Teacher proposed
Externí odkaz:
http://arxiv.org/abs/2210.11728
Magnetic Resonance Imaging (MRI) scans are time consuming and precarious, since the patients remain still in a confined space for extended periods of time. To reduce scanning time, some experts have experimented with undersampled k spaces, trying to
Externí odkaz:
http://arxiv.org/abs/2208.11472
Autor:
Pal, Arghya, Rathi, Yogesh
Publikováno v:
Journal of Machine Learning for Biomedical Imaging 2022
Following the success of deep learning in a wide range of applications, neural network-based machine-learning techniques have received significant interest for accelerating magnetic resonance imaging (MRI) acquisition and reconstruction strategies. A
Externí odkaz:
http://arxiv.org/abs/2109.08618
Publikováno v:
Indian Journal of Psychiatry. May2024, Vol. 66 Issue 5, p421-432. 12p.
In this work, we show the generative capability of an image classifier network by synthesizing high-resolution, photo-realistic, and diverse images at scale. The overall methodology, called Synthesize-It-Classifier (STIC), does not require an explici
Externí odkaz:
http://arxiv.org/abs/2103.14212
The paucity of large curated hand-labeled training data forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant supervision signals in the form of
Externí odkaz:
http://arxiv.org/abs/2005.00364
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Balhara, Yatan Pal Singh, Ghosh, Abhishek, Sarkar, Siddharth, Mahadevan, Jayant, Pal, Arghya, Narasimha, Venkata Lakshmi, Kattula, Dheeraj, Prasad, Sambhu, Parmar, Arpit, Kathiresan, Preethy, Basu, Anirudha, Bhatia, Gayatri, Shah, Raghav, Dhagudu, Naveen Kumar, Tripathi, Richa, Bharadwaj, Balaji
Publikováno v:
Advances in Dual Diagnosis, 2022, Vol. 15, Issue 4, pp. 227-243.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/ADD-09-2022-0025
In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner learns from t
Externí odkaz:
http://arxiv.org/abs/1903.01092