Výsledky vyhledávání - "Sangwoo Hong"

Akademický článek

NeRFlex: Flexible Neural Radiance Fields With Diffeomorphic Deformation

Autor: Jiyoon Shin, Sangwoo Hong, Jungwoo Lee

Publikováno v: IEEE Access, Vol 12, Pp 59920-59929 (2024)

Due to the vast array of NeRF-based techniques, the representation power of Neural Radiance Fields (NeRF) has been quickly rising in recent years. However, it is still difficult to offer fresh perspectives for user-controlled geometry alterations wit

Externí odkaz: https://doaj.org/article/bd7e516c35d941eaa1315e0f53d79956

Zobrazit plný text záznamu

Akademický článek

GBMix: Enhancing Fairness by Group-Balanced Mixup

Autor: Sangwoo Hong, Youngseok Yoon, Hyungjun Joo, Jungwoo Lee

Publikováno v: IEEE Access, Vol 12, Pp 18877-18887 (2024)

Mixup is a powerful data augmentation strategy that has been shown to improve the generalization and adversarial robustness of machine learning classifiers, particularly in computer vision applications. Despite its simplicity and effectiveness, the i

Externí odkaz: https://doaj.org/article/2e77c5614055405392aab5bbf121068f

Zobrazit plný text záznamu

Akademický článek

Securely Straggler-Exploiting Coded Computation for Distributed Matrix Multiplication

Autor: Heecheol Yang, Sangwoo Hong, Jungwoo Lee

Publikováno v: IEEE Access, Vol 9, Pp 167374-167388 (2021)

In this paper, we consider coded computation for matrix multiplication tasks in distributed computing, which can mitigate the effect of slow workers, called stragglers, using a coding approach. We assume that the straggler computation results can be

Externí odkaz: https://doaj.org/article/17c761700815473cb9b8db5ae0d7c943

Zobrazit plný text záznamu

Akademický článek

Squeezed Polynomial Codes: Communication-Efficient Coded Computation in Straggler-Exploiting Distributed Matrix Multiplication

Autor: Sangwoo Hong, Heecheol Yang, Jungwoo Lee

Publikováno v: IEEE Access, Vol 8, Pp 190516-190528 (2020)

In a distributed computing environment, there may exist slow processing workers, which are known as “stragglers”, and they can slow down the whole computing process. In this article, we consider coded computation for matrix multiplication tasks i

Externí odkaz: https://doaj.org/article/3f821a3cde074d6cbb27deab7003c52a

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání