Zobrazeno 1 - 10
of 642
pro vyhledávání: '"Pham, Tung"'
There has long been plenty of theoretical and empirical evidence supporting the success of ensemble learning. Deep ensembles in particular take advantage of training randomness and expressivity of individual neural networks to gain prediction diversi
Externí odkaz:
http://arxiv.org/abs/2403.13204
Autor:
Tran, Ngoc N., Tran, Lam, Phan, Hoang, Bui, Anh, Pham, Tung, Tran, Toan, Phung, Dinh, Le, Trung
Contrastive learning (CL) is a self-supervised training paradigm that allows us to extract meaningful features without any label information. A typical CL framework is divided into two phases, where it first tries to learn the features from unlabelle
Externí odkaz:
http://arxiv.org/abs/2311.09671
Autor:
Nguyen, Ngoc Bich, Nguyen, Ngu Huu, Tran, Duc Thanh, Tran, Phuong Thi, Pham, Tung Gia, Nguyen, Tri Minh
This study aims to create a flood extent map with Sentinel imagery and to evaluate impacts on agricultural land in the lagoon region of central Vietnam. In this study, remote sensing images, obtained from 2017 to 2019, were used to simultaneously map
Externí odkaz:
https://tud.qucosa.de/id/qucosa%3A77153
https://tud.qucosa.de/api/qucosa%3A77153/attachment/ATT-0/
https://tud.qucosa.de/api/qucosa%3A77153/attachment/ATT-0/
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ black-box a
Externí odkaz:
http://arxiv.org/abs/2310.00567
Autor:
Truong, Tuan, Nguyen, Hoang-Phi, Pham, Tung, Tran, Minh-Tuan, Harandi, Mehrtash, Phung, Dinh, Le, Trung
Nowadays, understanding the geometry of the loss landscape shows promise in enhancing a model's generalization ability. In this work, we draw upon prior works that apply geometric principles to optimization and present a novel approach to improve rob
Externí odkaz:
http://arxiv.org/abs/2309.17215
Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks. In this paper, we consider classification as a downstream task in phase 2 and develop rigorous theories to realize the factors that implici
Externí odkaz:
http://arxiv.org/abs/2305.10252
Autor:
Bui, Linh P, Pham, Tung T, Wang, Fenglei, Chai, Boyang, Sun, Qi, Hu, Frank B, Lee, Kyu Ha, Guasch-Ferre, Marta, Willett, Walter C
Publikováno v:
In The American Journal of Clinical Nutrition July 2024 120(1):80-91
We study the entropic Gromov-Wasserstein and its unbalanced version between (unbalanced) Gaussian distributions with different dimensions. When the metric is the inner product, which we refer to as inner product Gromov-Wasserstein (IGW), we demonstra
Externí odkaz:
http://arxiv.org/abs/2108.10961
Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications. Despite their practicality, m-OT suffers from misspecified mappings, namely, mappings that are optimal on the mini-batc
Externí odkaz:
http://arxiv.org/abs/2108.09645