Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Shin, JaeWoong"'
Deep learning has shown great potential in assisting radiologists in reading chest X-ray (CXR) images, but its need for expensive annotations for improving performance prevents widespread clinical application. Visual language pre-training (VLP) can a
Externí odkaz:
http://arxiv.org/abs/2304.05303
Autor:
Ryu, Jeongun, Puche, Aaron Valero, Shin, JaeWoong, Park, Seonwook, Brattoli, Biagio, Lee, Jinhee, Jung, Wonkyung, Cho, Soo Ick, Paeng, Kyunghyun, Ock, Chan-Young, Yoo, Donggeun, Pereira, Sérgio
Cell detection is a fundamental task in computational pathology that can be used for extracting high-level medical information from whole-slide images. For accurate cell detection, pathologists often zoom out to understand the tissue-level structures
Externí odkaz:
http://arxiv.org/abs/2303.13110
DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR, enhances th
Externí odkaz:
http://arxiv.org/abs/2111.14330
Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters. Although such hyperparameters can be optimized using the existing gradient-based hyperpara
Externí odkaz:
http://arxiv.org/abs/2110.02508
Publikováno v:
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9603-9613, 2021
Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framework to many-shot scenarios, which may further enhance its practicality, has been relatively overlooked
Externí odkaz:
http://arxiv.org/abs/2102.07215
Regularization and transfer learning are two popular techniques to enhance generalization on unseen data, which is a fundamental problem of machine learning. Regularization techniques are versatile, as they are task- and architecture-agnostic, but th
Externí odkaz:
http://arxiv.org/abs/2006.07540
Publikováno v:
Lee, H B, Lee, H, Shin, J, Yang, E, Hospedales, T & Hwang, S J 2022, Online Hyperparameter Meta-Learning with Hypergradient Distillation . in International Conference on Learning Representations (ICLR 2022) . Tenth International Conference on Learning Representations 2022, 25/04/22 . < https://openreview.net/forum?id=01AMRlen9wJ >
Many gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization, which can be considered as hyperparameters. Although such hyperparameters can be optimized using the existing gradient-based hyperpara
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3094::219a3cc48e081e745a42424845d0165c
https://www.pure.ed.ac.uk/ws/files/253268247/Online_Hyperparameter_LEE_DOA34012022_AFV.pdf
https://www.pure.ed.ac.uk/ws/files/253268247/Online_Hyperparameter_LEE_DOA34012022_AFV.pdf
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.