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/text corruptions. Such corruptions are often unobserved during the training, and degrade the retrieval model’s 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 (SPAug-I) and text (SPAug-T). Since SPAug-I and SPAug-T 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’s robustness significantly. From extensive experiments using benchmark datasets, we show that RVSE outperforms conventional retrieval schemes in terms of image-text retrieval performance.

Federated learning is a machine learning framework that enables AI models training over a network of multiple user devices without revealing user data stored in the devices. Popularly used federated learning technique to enhance the learning performance of user devices is to globally evaluate the learning model at the server by averaging the locally trained models of the devices. This global model is then sent back to the user devices so that every device applies it in the next training iteration. However, this average-based model is not always better than the local update model of a user device. In this work, we put forth a new update strategy based on the simulated annealing (SA) algorithm, in which the user devices choose their training parameters between the global evaluation model and their local models probabilistically. The proposed technique, dubbed simulated annealing-based federated learning (SAFL), is effective in solving a wide class of federated learning problems. From numerical experiments, we demonstrate that SAFL outperforms the conventional approach on different benchmark datasets, achieving an accuracy improvement of 50% in a few iterations.

In this paper, we propose a deep neural network based matrix completion approach for Internet of Things (IoT) localization. In the proposed method, we recast Euclidean distance matrix completion problem into the alternating minimization problem. By using a cascade of multiple deep neural networks to recover the location map of sensors (and the original distance matrix) from the noisy observed matrix, the proposed method can achieve an accurate reconstruction performance of the distance matrix. The numerical simulations demonstrate that the proposed method outperforms state-of-the-art matrix completion algorithms both in noisy and noiseless scenarios.

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) ≥ 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 + [r/L] iterations, provided that A satisfies the restricted isometry property (RIP) of order L(K - r) + r + 1 %/L with δL(K-r)+r+1[7.8K]≤ 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.

Location awareness, providing the ability to identify the location of sensor, machine, vehicle, and wearable device, is a rapidly growing trend of hyper-connected society and one of the key ingredients for the 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. The 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 localization in Riemannian manifold using conjugate gradient (LRM-CG) 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 LRM-CG, is effective in recovering the Euclidean distance matrix.