Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Molahasani, Mahdiyar"'
Publikováno v:
Proceedings of the SPIE, Volume 13097, id. 1309783 10 pp. (2024)
Adaptive optics (AO) systems are crucial for high-resolution astronomical observations by compensating for atmospheric turbulence. While laser guide stars (LGS) address high-order wavefront aberrations, natural guide stars (NGS) remain vital for low-
Externí odkaz:
http://arxiv.org/abs/2410.12084
We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that al
Externí odkaz:
http://arxiv.org/abs/2405.16304
A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection. While recent pedestrian detection models have achieved impressive performance on various datasets, they remain sensitive to
Externí odkaz:
http://arxiv.org/abs/2306.15117
The Long-Tailed Recognition (LTR) problem emerges in the context of learning from highly imbalanced datasets, in which the number of samples among different classes is heavily skewed. LTR methods aim to accurately learn a dataset comprising both a la
Externí odkaz:
http://arxiv.org/abs/2306.13275
Autor:
Zand, Mohsen, Damirchi, Haleh, Farley, Andrew, Molahasani, Mahdiyar, Greenspan, Michael, Etemad, Ali
We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multis
Externí odkaz:
http://arxiv.org/abs/2202.09942
Autor:
Jackson, Kathryn J., Schmidt, Dirk, Vernet, Elise, Taheri, Mojtaba, Molahasani, Mahdiyar, Ragland, Sam, Neichel, Benoit, Wizinowich, Peter
Publikováno v:
Proceedings of SPIE; August 2024, Vol. 13097 Issue: 1 p1309783-1309783-10
