Zobrazeno 1 - 10
of 761
pro vyhledávání: '"Kim, Suhyun"'
Autor:
Kim, Suhyun
甲第25045号
文博第950号
(主査)准教授 Stephane Heim, 教授 Mitsuyo Wada-Marciano, 准教授 丸山 里美, 教授 松田 素二
学位規則第4条第1項該当
Doctor of Letters
Kyoto University
DGAM
文博第950号
(主査)准教授 Stephane Heim, 教授 Mitsuyo Wada-Marciano, 准教授 丸山 里美, 教授 松田 素二
学位規則第4条第1項該当
Doctor of Letters
Kyoto University
DGAM
Externí odkaz:
http://hdl.handle.net/2433/288479
Autor:
Lim, Sumin, Kang, Sungsam, Hong, Jin-Hee, Jin, Youngho, Gupta, Kalpak, Kim, Moonseok, Kim, Suhyun, Choi, Wonshik, Yoon, Seokchan
Fluorescence imaging in thick biological tissues is challenging due to sample-induced aberration and scattering, which leads to severe degradation of image quality and resolution. Fluorescence imaging in reflection geometry further exacerbates this i
Externí odkaz:
http://arxiv.org/abs/2404.11849
Autor:
Park, Mincheol, Kim, Dongjin, Park, Cheonjun, Park, Yuna, Gong, Gyeong Eun, Ro, Won Woo, Kim, Suhyun
Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning granularity
Externí odkaz:
http://arxiv.org/abs/2402.17862
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2024, 2705-2713
Deep learning has made significant advances in computer vision, particularly in image classification tasks. Despite their high accuracy on training data, deep learning models often face challenges related to complexity and overfitting. One notable co
Externí odkaz:
http://arxiv.org/abs/2401.13193
Autor:
Park, Dogyun, Kim, Suhyun
Assessing the fidelity and diversity of the generative model is a difficult but important issue for technological advancement. So, recent papers have introduced k-Nearest Neighbor ($k$NN) based precision-recall metrics to break down the statistical d
Externí odkaz:
http://arxiv.org/abs/2309.01590
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 2022, 1201-1209
We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data. In NaturalInversion, we propose: (1) a Feature Transfer Pyramid which uses enhanced
Externí odkaz:
http://arxiv.org/abs/2306.16661
Autor:
Kang, Minsoo, Kim, Suhyun
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 2023, 1096-1104
Data augmentation is now an essential part of the image training process, as it effectively prevents overfitting and makes the model more robust against noisy datasets. Recent mixing augmentation strategies have advanced to generate the mixup mask th
Externí odkaz:
http://arxiv.org/abs/2306.16612
Autor:
Kim, Suhyun
Publikováno v:
Journal of Asian Sociology, 2023 Dec 01. 52(4), 239-268.
Externí odkaz:
https://www.jstor.org/stable/27283021
Autor:
Kang, Hyeryung, Kim, Suhyun, Park, Sungyeon, Han, Sila, Kang, Minsoo, Kwon, Sujin, Ko, Jesang
Publikováno v:
In Experimental Cell Research 1 October 2024 442(2)
Autor:
Park, Wonbeom, Park, Myungseo, Chun, Jihwan, Hwang, Jaehyeon, Kim, Suhyun, Choi, Nayoon, Kim, Soo min, Kim, SeungJoo, Jung, Sangwon, Ko, Kwan Soo, Kweon, Dae-Hyuk
Publikováno v:
In International Journal of Antimicrobial Agents August 2024 64(2)