Výsledky vyhledávání - "Chung, Taechoong"

Report

SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization

Autor: Uddin, A. F. M. Shahab, Monira, Mst. Sirazam, Shin, Wheemyung, Chung, TaeChoong, Bae, Sung-Ho

Publikováno v: International Conference On Learning Representations (ICLR) 2021

Advanced data augmentation strategies have widely been studied to improve the generalization ability of deep learning models. Regional dropout is one of the popular solutions that guides the model to focus on less discriminative parts by randomly rem

Externí odkaz: http://arxiv.org/abs/2006.01791

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

Center Emphasized Visual Saliency and a Contrast-based Full Reference Image Quality Index

Autor: Layek, Md Abu, Afroz, Sanjida, Chung, TaeChoong, Huh, Eui-Nam

Publikováno v: Symmetry 2019, 11, 296. Online: https://www.mdpi.com/2073-8994/11/3/296

Objective image quality assessment (IQA) is imperative in the current multimedia-intensive world, in order to assess the visual quality of an image at close to a human level of ability. Many~parameters such as color intensity, structure, sharpness, c

Externí odkaz: http://arxiv.org/abs/1812.11163

Zobrazit plný text záznamu

Report

Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes

Autor: Tuyen, Le Pham, Vien, Ngo Anh, Layek, Abu, Chung, TaeChoong

In recent years, reinforcement learning has achieved many remarkable successes due to the growing adoption of deep learning techniques and the rapid growth in computing power. Nevertheless, it is well-known that flat reinforcement learning algorithms

Externí odkaz: http://arxiv.org/abs/1805.04419

Zobrazit plný text záznamu