arXiv subjects

Luong Trung Nguyen

Publications and source records attributed to Luong Trung Nguyen.

5 recordsLinked to original sources

arXiv2023

Semantic-Preserving Augmentation for Robust Image-Text Retrieval

Image text retrieval is a task to search for the proper textual descriptions of the visual world and vice versa. One challenge of this task is the vulnerability to input image and text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model decision quality substantially. In this paper, we propose a novel image text retrieval technique, referred to as robust visual semantic embedding (RVSE), which consists of novel image-based and text-based augmentation techniques called semantic preserving augmentation for image (SPAugI) and text (SPAugT). Since SPAugI and SPAugT change the original data in a way that its semantic information is preserved, we enforce the feature extractors to generate semantic aware embedding vectors regardless of the corruption, improving the model robustness significantly. From extensive experiments using benchmark datasets, we show that RVSE outperforms conventional retrieval schemes in terms of image-text retrieval performance.

cs.CV↗

arXiv2021

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 \textit{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.

cs.LG↗

arXiv2020

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 $\mathbf{A}$ satisfies $\text{krank}(\mathbf{A}) \ge K+1$, which meets the fundamental minimum requirement on $\mathbf{A}$ to ensure exact recovery. We also show that SSMP guarantees exact reconstruction in at most $K-r+\lceil \frac{r}{L} \rceil$ iterations, provided that $\mathbf{A}$ satisfies the restricted isometry property (RIP) of order $L(K-r)+r+1$ with $$δ_{L(K-r)+r+1} < \max \left \{ \frac{\sqrt{r}}{\sqrt{K+\frac{r}{4}}+\sqrt{\frac{r}{4}}}, \frac{\sqrt{L}}{\sqrt{K}+1.15 \sqrt{L}} \right \},$$ 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 further show that if $r=1$, then by running more than $K$ iterations, the performance guarantee of SSMP can be improved to $δ_{\lfloor 7.8K \rfloor} \le 0.155$. In addition, 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 stability of SSMP under measurement noise. Finally, from extensive numerical experiments, we show that SSMP outperforms conventional joint sparse recovery algorithms both in noiseless and noisy scenarios.

cs.IT↗

arXiv2019

Low-Rank Matrix Completion: A Contemporary Survey

As a paradigm to recover unknown entries of a matrix from partial observations, low-rank matrix completion (LRMC) has generated a great deal of interest. Over the years, there have been lots of works on this topic but it might not be easy to grasp the essential knowledge from these studies. This is mainly because many of these works are highly theoretical or a proposal of new LRMC technique. In this paper, we give a contemporary survey on LRMC. In order to provide better view, insight, and understanding of potentials and limitations of LRMC, we present early scattered results in a structured and accessible way. Specifically, we classify the state-of-the-art LRMC techniques into two main categories and then explain each category in detail. We next discuss issues to be considered when one considers using LRMC techniques. These include intrinsic properties required for the matrix recovery and how to exploit a special structure in LRMC design. We also discuss the convolutional neural network (CNN) based LRMC algorithms exploiting the graph structure of a low-rank matrix. Further, we present the recovery performance and the computational complexity of the state-of-the-art LRMC techniques. Our hope is that this survey article will serve as a useful guide for practitioners and non-experts to catch the gist of LRMC.

cs.DS↗

arXiv2019

Matrix Completion Based Localization in the Internet of Things Network

In order to make a proper reaction to the collected information from internet of things (IoT) devices, location information of things should be available at the data center. One challenge for the massive IoT networks is to identify the location map of whole sensor nodes from partially observed distance information. In this paper, we propose a matrix completion based localization algorithm to reconstruct the location map of sensors using partially observed distance information. From the numerical experiments, we show that the proposed method based on the modified conjugate gradient is effective in recovering the Euclidean distance matrix.

cs.IT↗