Luong Trung Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Luong Trung Nguyen has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Junhan Kim
Department of Electrical and Computer Engineering Seoul National University Seoul Korea
5 shared publications - Byonghyo Shim
Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, Seoul, Republic of Korea
4 shared publications B. Appelbe
Department of Computer Science, RMIT University, Australia
1 shared publicationByonghyo Shim
Department of Electrical and Computer Engineering, Seoul National University, Gwanak-gu, Seoul, South Korea
1 shared publication- Jian Wang
Fudan University
1 shared publication - Kyuhong Shim
Department of Electrical and Computer Engineering Seoul National University Korea
1 shared publication
Latest Publications
- Open Access
- 7 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 19401-19411
Pseudo-Label-Free Weakly Supervised Semantic Segmentation Using Image Masking
Weakly-supervised semantic segmentation (WSSS) aims to train a semantic segmentation network using weak labels. Recent approaches generate the pseudo-label from the image-level label and then exploit it as a pixel-level supervision in the segmentation network training. A potential drawback of the conventional WSSS approaches is that the pseudo-label cannot accurately express the object regions and their classes, causing a degradation of the segmentation performance. In this paper, we propose a new WSSS technique that trains the segmentation network without relying on the pseudo-label. Key idea of the proposed approach is to train the segmentation network such that the object erased by the segmentation map is not detected by the classification network. From extensive experiments on the PASCAL VOC 2012 benchmark dataset, we demonstrate that our approach is effective in WSSS.
- 7 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 19401-19411
Open AccessPseudo-Label-Free Weakly Supervised Semantic Segmentation Using Image Masking
Weakly-supervised semantic segmentation (WSSS) aims to train a semantic segmentation network using weak labels. Recent approaches generate the pseudo-label from the image-level label and then exploit it as a pixel-level supervision in the segmentation network training. A potential drawback of the conventional WSSS approaches is that the pseudo-label cannot accurately express the object regions and their classes, causing a degradation of the segmentation performance. In this paper, we propose a new WSSS technique that trains the segmentation network without relying on the pseudo-label. Key idea of the proposed approach is to train the segmentation network such that the object erased by the segmentation map is not detected by the classification network. From extensive experiments on the PASCAL VOC 2012 benchmark dataset, we demonstrate that our approach is effective in WSSS.
- 4 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 69 (1053587X) , 6299-6313
Gradual Federated Learning With Simulated Annealing
Federated averaging (FedAvg) is a popular federated learning (FL) technique that updates the global model by averaging local models and then transmits the updated global model to devices for their local model update. One main limitation of FedAvg is that the average-based global model is not necessarily better than local models in the early stage of the training process so that FedAvg might diverge in realistic scenarios, especially when the data is non-identically distributed across devices and the number of data samples varies significantly from device to device. In this paper, we propose a new FL technique based on simulated annealing. The key idea of the proposed technique, henceforth referred to as simulated annealing-based FL (SAFL), is to allow a device to choose its local model when the global model is immature. Specifically, by exploiting the simulated annealing strategy, we make each device choose its local model with high probability in early iterations when the global model is immature. From extensive numerical experiments using various benchmark datasets, we demonstrate that SAFL outperforms the conventional FedAvg technique in terms of the convergence speed and the classification accuracy.
- 4 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 69 (1053587X) , 6299-6313
Gradual Federated Learning With Simulated Annealing
Federated averaging (FedAvg) is a popular federated learning (FL) technique that updates the global model by averaging local models and then transmits the updated global model to devices for their local model update. One main limitation of FedAvg is that the average-based global model is not necessarily better than local models in the early stage of the training process so that FedAvg might diverge in realistic scenarios, especially when the data is non-identically distributed across devices and the number of data samples varies significantly from device to device. In this paper, we propose a new FL technique based on simulated annealing. The key idea of the proposed technique, henceforth referred to as simulated annealing-based FL (SAFL), is to allow a device to choose its local model when the global model is immature. Specifically, by exploiting the simulated annealing strategy, we make each device choose its local model with high probability in early iterations when the global model is immature. From extensive numerical experiments using various benchmark datasets, we demonstrate that SAFL outperforms the conventional FedAvg technique in terms of the convergence speed and the classification accuracy.
- 1 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (10) , 2115-2119
Deep Learning Based Low-Rank Matrix Completion for IoT Network Localization
In this letter, we propose a deep learning-based technique to recover a Euclidean distance matrix D in IoT network localization. In contrast to conventional localization algorithms that search D over a whole set of matrices, the proposed technique, called multiple deep neural networks for localization (MDNL), estimates D over the set of Euclidean distance matrices. Other than the low-rank constraint, a Euclidean distance matrix is symmetric, and its diagonal and non-diagonal entries are zero and positive, respectively. To exploit these properties in recovering D , we express D as a function of the sensor coordinate matrix that ensures the symmetry and zero diagonal and positive non-diagonal entries of D , and then jointly recover D and the sensor coordinate matrix by employing deep neural network. Numerical results demonstrate that the proposed MDNL technique not only brings significant performance gain over conventional localization approaches in the noiseless scenario, but it also shows competitive recovery performance in the presence of noise.
- 1 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (10) , 2115-2119
Deep Learning Based Low-Rank Matrix Completion for IoT Network Localization
In this letter, we propose a deep learning-based technique to recover a Euclidean distance matrix D in IoT network localization. In contrast to conventional localization algorithms that search D over a whole set of matrices, the proposed technique, called multiple deep neural networks for localization (MDNL), estimates D over the set of Euclidean distance matrices. Other than the low-rank constraint, a Euclidean distance matrix is symmetric, and its diagonal and non-diagonal entries are zero and positive, respectively. To exploit these properties in recovering D , we express D as a function of the sensor coordinate matrix that ensures the symmetry and zero diagonal and positive non-diagonal entries of D , and then jointly recover D and the sensor coordinate matrix by employing deep neural network. Numerical results demonstrate that the proposed MDNL technique not only brings significant performance gain over conventional localization approaches in the noiseless scenario, but it also shows competitive recovery performance in the presence of noise.
- 9 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 66 (8) , 5072-5096
Joint Sparse Recovery Using Signal Space Matching Pursuit
In this paper, we put forth a new joint sparse recovery algorithm called signal space matching pursuit (SSMP). The key idea of the proposed SSMP algorithm is to sequentially investigate the support of jointly sparse vectors to minimize the subspace distance to the residual space. Our performance guarantee analysis indicates that SSMP accurately reconstructs any row K-sparse matrix of rank r in the full row rank scenario if the sampling matrix A satisfies krank(A) δ K+1, which meets the fundamental minimum requirement on A to ensure exact recovery. We also show that SSMP guarantees exact reconstruction in at most K − r + d r Le iterations, provided that A satisfies the restricted isometry property (RIP) of order L(K − r) + r + 1 with δL(K−r)+r+1 < max { √r/√K + r/4 + √r/4, √l/√k + 1.15√L}, where L is the number of indices chosen in each iteration. This implies that the requirement on the RIP constant becomes less restrictive when r increases. Such behavior seems to be natural but has not been reported for most of conventional methods. We also show that if r = 1, then by running more than K iterations, the performance guarantee of SSMP can be improved to δ7.8K| ≤ 0.155. Furthermore, we show that under a suitable RIP condition, the reconstruction error of SSMP is upper bounded by a constant multiple of the noise power, which demonstrates the robustness of SSMP to measurement noise. Finally, from extensive numerical experiments, we show that SSMP outperforms conventional joint sparse recovery algorithms both in noiseless and noisy scenarios.
- 9 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 66 (8) , 5072-5096
Joint Sparse Recovery Using Signal Space Matching Pursuit
In this paper, we put forth a new joint sparse recovery algorithm called signal space matching pursuit (SSMP). The key idea of the proposed SSMP algorithm is to sequentially investigate the support of jointly sparse vectors to minimize the subspace distance to the residual space. Our performance guarantee analysis indicates that SSMP accurately reconstructs any row K-sparse matrix of rank r in the full row rank scenario if the sampling matrix A satisfies krank(A) δ K+1, which meets the fundamental minimum requirement on A to ensure exact recovery. We also show that SSMP guarantees exact reconstruction in at most K − r + d r Le iterations, provided that A satisfies the restricted isometry property (RIP) of order L(K − r) + r + 1 with δL(K−r)+r+1 < max { √r/√K + r/4 + √r/4, √l/√k + 1.15√L}, where L is the number of indices chosen in each iteration. This implies that the requirement on the RIP constant becomes less restrictive when r increases. Such behavior seems to be natural but has not been reported for most of conventional methods. We also show that if r = 1, then by running more than K iterations, the performance guarantee of SSMP can be improved to δ7.8K| ≤ 0.155. Furthermore, we show that under a suitable RIP condition, the reconstruction error of SSMP is upper bounded by a constant multiple of the noise power, which demonstrates the robustness of SSMP to measurement noise. Finally, from extensive numerical experiments, we show that SSMP outperforms conventional joint sparse recovery algorithms both in noiseless and noisy scenarios.
- 7 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 67 (8) , 5833-5847
Localization of IoT Networks via Low-Rank Matrix Completion
Location awareness, providing ability to identify the location of sensor, machine, vehicle, and wearable device, is a rapidly growing trend of hyper-connected society and one of key ingredients for internet of things (IoT) era. In order to make a proper reaction to the collected information from things, location information of things should be available at the data center. One challenge for the IoT networks is to identify the location map of whole nodes from partially observed distance information. An aim of this paper is to present an algorithm to recover the Euclidean distance matrix (and eventually the location map) from partially observed distance information. By casting the low-rank matrix completion problem into the unconstrained minimization problem in a Riemannian manifold in which a notion of differentiability can be defined, we solve the low-rank matrix completion problem using a modified conjugate gradient algorithm. From the convergence analysis, we show that LRMCG converges linearly to the original Euclidean distance matrix under the extended Wolfe’s conditions. From the numerical experiments, we demonstrate that the proposed method, called localization in Riemannian manifold using conjugate gradient (LRMCG), is effective in recovering the Euclidean distance matrix.
- 7 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 67 (8) , 5833-5847
Localization of IoT Networks via Low-Rank Matrix Completion
Location awareness, providing ability to identify the location of sensor, machine, vehicle, and wearable device, is a rapidly growing trend of hyper-connected society and one of key ingredients for internet of things (IoT) era. In order to make a proper reaction to the collected information from things, location information of things should be available at the data center. One challenge for the IoT networks is to identify the location map of whole nodes from partially observed distance information. An aim of this paper is to present an algorithm to recover the Euclidean distance matrix (and eventually the location map) from partially observed distance information. By casting the low-rank matrix completion problem into the unconstrained minimization problem in a Riemannian manifold in which a notion of differentiability can be defined, we solve the low-rank matrix completion problem using a modified conjugate gradient algorithm. From the convergence analysis, we show that LRMCG converges linearly to the original Euclidean distance matrix under the extended Wolfe’s conditions. From the numerical experiments, we demonstrate that the proposed method, called localization in Riemannian manifold using conjugate gradient (LRMCG), is effective in recovering the Euclidean distance matrix.
- 7 November 2002
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 158-169
A set approach to role modeling
- 7 November 2002
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 158-169
A set approach to role modeling